A Transforming Visual Analysis Approach for the Recognition of Colletotrichum Falcatum Leading to Red Rot of Sugarcane

http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1430 A Transforming Visual Analysis Approach for the Recognition of Colletotrichum Falcatum Leading to Red Rot of Sugarcane Usman Ahmed Department of Computer Sciences, The University of Faisalabad, Faisalabad, Punjab, Pakistan Email: [email protected] Abdul Rauf* Department of Computer Sciences, The University of Faisalabad, Faisalabad, Punjab, Pakistan Email: [email protected] Majid Hussain Department of Computer Sciences, The University of Faisalabad, Faisalabad, Punjab, Pakistan Email: [email protected] Rana Hassam Ahmed Department of Computer Sciences, The University of Faisalabad, Faisalabad, Punjab, Pakistan Email: [email protected] The identification of Colletotrichum Falcatum in sugarcane has become a major global concern. A major contributor to sugarcane diseases is Colletotrichum Falcatum that triggers red rot disease in sugarcane. Multiple techniques are being developed to detect this type of disorder. Earlier studies have adopted k-nearest neighbors (KNN), Support Vector Machine (SVM), and Neural Network (NN) to discover Collectotrichum Falcatum red rot disease in sugarcane. The approaches currently in development for detecting Collectorichum falcutm are inefficient. These methods need the extraction of characteristics from images of sugarcane, which is used to identify Collectotrichum falciparum disease. Red rot infection was discovered in 88.2% of the measured fields. An estimate of the total losses in sugarcane output was 20.1%.[1] This study suggests a fast and efficient image-based approach called Faster Regionbased Convolutional Neural Network (R-CNN) for the identification of Collectotrichum Falcatum sugarcane infections. Region Proposal Network (RPN) fixes selective search, whereas Faster R-CNN handles it. Convolutional Neural Network (CNN) is used to first extract feature maps from the input image, which are then sent through an RPN to provide object recommendations. The datasets of sugarcane images are available at GitHub, which have approximately ninety thousand photographs available for free, are the source of the sugarcane datasets. Not many photos are taken directly using a cell phone. The approach is trained and tested using these images. A comparison is made between the proposed approach and K Nearest A B S T R A C T http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1431 Neighbor (KNN). The experimental findings demonstrate that the suggested method outperforms the current method. Faster R-CNN If compared to KNN, sugarcane disease detection is more effective. Faster R-CNN achieved a detection rate of 0.96, whereas KNN produced 0.91. Furthermore, accuracy climbed to 0.98 whereas KNN generated 0.83. Keywords: AI, CNN, DNN, DRNN, KNN, RPN, Neural Network, Principal Component Analysis, and Support Vector Machine. INTRODUCTION As sugarcane enhances the financial livelihood of many sugarcane producers, it is considered one of the basic money crops [2]. Despite the fact that we use sugar in our daily lives. About 1.9 billion tons of sugarcane are produced annually on an estimated 26.3 million hectares of land. The major producers of sugarcane are the USA, Mexico, Thailand, China, India, Pakistan, and Thailand. Despite widespread concerns about excessive global sugar consumption, sugarcane consumption on a daily basis is increasing, especially in agricultural nations where per capita consumption is often modest. The sugar business, especially in sugarcane developing countries, is playing a crucial role in improving the financial situation of many people via asset preparation, work, and rural infrastructural development. Sugarcane is a major commercial crop that is grown all over the world and is the main source of both sugar and ethanol, among other things [3]. It gives in to a variety of infections, including red rot caused by the infectious microbe. Falcatum Colletotrichum A devastating virus called went has led to the demise of many cultivars in the past. With a hemibiotrophic lifestyle, Colletotrichum Falcatum first colonizes its host biotrophically before transitioning to a necrotrophic stage. Specific disease structures, such as entrance stakes, appressoria, necessary and optional hyphae, and finally a biogenetic fruiting designs called "acervuli" that contain conidia and paraphyses, are produced by the organisms during the sickness cycle. In this race towards advancement, new pathotypes of Colletotrichum Falcatum keep on emerging, and one variety after another breaks down in the field. During the past few years, massive efforts have been made towards enhancing our understanding of the host–microbe relationship with regard to the molecular basis of resistance to red rot. If the association is to accord better, it must make use of the modern tools at its disposal to develop the life cycle of the microorganism inside the host tissue. Sugarcane is a key marketable crop in Guangxi [4], and sugarcane disease which includes abnormalities, microscopic organisms, infectious diseases, root hitch worms, and parasitic seed plants; largely influences the cultivation of this crop. Colletotrichum Falcatum, one of the worst diseases, has a complicated wormhole in the sugarcane tail that has a real impact on the formation and development of sugar sticks. The local farmers in Chongzuo Qujiu stated that if sugarcane was ever chewed by a sugarcane drill, it could not be planted at that time. As a result, selecting infected sugarcane seeds prior to planting was crucial. In addition to seed recognition, screening plays an essential function in the growth and development of crops. http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1432 Growing to a height of two to four meters, sugarcane is a tall tropical perennial grass [5]. Sugarcane is used to produce a variety of foods, such as sugar, molasses, and maple syrup. Ethanol biofuel may also be generated from sugarcane, which is a fuel that can be consumed in its pure form for vehicles but is usually combined with gasoline to boost emission levels. Planting is the main method of expanding sugarcane. The sections of a juvenile stick's tail that are used for planting are called "seed sticks," or stick sets, and they usually have three buds, or at least two eyes. Sticks of seed are sown in heavily labored fields. There are 68 countries that supply sugarcane that have red rot [2]. The disease decreases sugarcane production by fifty percent. However, only 31% of the sugar is recovered. In addition to reducing output, red rot lowers the quality of sugarcane juice which is measured by sucrose content, virtue, Brix and its natural sweetener value. Although the infection's damaging effects are the main cause of the withdrawal of the many sugarcane varieties from sugarcane development globally, red rot sickness is a serious disease. The geographical origins of the many variants in the morphologic and pathologic characteristics of the Colletotrichum class are used to identify them. However, separating evidence using morphologic methods is insufficient due of the unbelievable number of covering behaviors within the species. Furthermore, managing red rot disease in the field poses challenges due to the everchanging genetic code within this microorganism. Therefore, accurate and swift recognizing evidence of Colletotrichum Falcatum is crucial. Due to the ongoing failure of the reliable plant variety, no red rot infection executive has been successful up till this point. Replicators must be aware of the red rot microbe's races in order to make safe crops. Data on early detection and control strategies for Colletotrichum Falcatum are limited. The goals of this study were the following: Introduce an overview of the existing field and research center protocols for early detection of red rot infection and red rot disease control. Assess the effectiveness of red rot infectious prevention surveys [2] in order to suggest more effective methods for preventing the spread of Colletotrichum Falcatum. Shrinkage of sugarcane was documented more than a century ago [6]. From then on, it seriously hampered the nation's progress. Recent research conducted by the Institute revealed that infections have occurred to varying degrees in almost all of the nation's sugarcane developing states. The disease affected many of the well-known varieties that were being cultivated. Previous studies conducted in India revealed that the disease occurs four to five months after harvest. Regardless, throughout the germination and tillering stages of sugarcane, concentrations that separated from their excessive articulation during the harvest's remarkable development periods in the growing area die. The results show that the fungus not only causes red rot in sugarcane plants but also lowers the amount of proteins and carbohydrates in the plant, which in turn lowers the quality of the sugar and might have a significant impact on the crop's value.[7] Red rot is associated with Colletotrichum Falcatum [8], a disease that is considered crucial in all developing countries that cultivate sugarcane. In any case, the more evident negative effect and disaster are observed in the end. The bacteria is simply sett transmitted and causes infection in all stages of harvest. Red rot disease on sugarcane drastically reduces stick yield and affects the parameters of juice quality, http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1433 such as Brix value, sucrose content, cleanliness, and commercial pure sugar. Due to red rot infection, sugarcane yield disaster has been shown to range from 28 to 82%. In a few number of sugar production line regions, yield loss due to red rot has also been documented to be 100%. The bacteria reduced extraction by 32.5%, business stick sugar by 39%, and sucrose content by 25–75%. Red rot continues to be a very old and challenging problem in the development of sugarcane, negatively impacting stockman jobs and financially ruining sugarcane-based industries throughout the whole country. Fig 1. Colletotrichum Falcatum Disease [2] Fig 2. Colletotrichum Falcatum Disease [3] http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1434 The images of sugarcane damaged by Collectorichum Falcatum disease are displayed in both Figures 1 and 2. The vector representation of the fungus that causes Collectorichum Falcatum can be observed in Figure 2. The structure of the paper is as follows: The related research study regarding sugarcane infection detection is presented in Section II. Section III describes the suggested method of recognizing red rot. The results and evaluation are provided in Section IV. The final section contains an overview of the research and recommendations for its future prospects. RELATED WORK Several analysts have developed approaches to categorizing and recognizing sugarcane infection [9], using image processing to extract the key elements from the plant and then determine if it is unhealthy. The plant leaf's surface was investigated using a shading change structure, and an SVM classifier was then applied to determine the infection's nature. In addition to advanced image setup, K-implies gathering and computer reasoning were used to identify patterns for crop diseases. On the leaf, Gabor screening and segmentation were carried out. To identify the infection in sugarcane, a discrete frequency change method was applied, and a decision tree was used to complete the image character development. Extreme learning machine (ELM) was used to predict how sugarcane will grow in various regions of the nation. The ELM model performed better when examined using the standard ANN algorithm, according to the results. Red rot related to Colletotrichum Falcatum is considered a disease that is critical in all developing countries that produce sugarcane [8]. Red rot originated in Asia following a series of epidemics that were reported in various regions of the country. Due to red rot disease, sugarcane yield tragedy has been documented to range from 28 to 82%. In places with very few sugar producing plants, red rot has also been reported to be the sole cause of harvest loss. The growth of all solvent salts, sharpness, lowering sugars, and decrease in sucrose as well as the cleanness of sugarcane juice were observed in sticks affected by red rot. The microorganism reduced extraction by 32.5%, stick sugar by 39%, and sucrose content by 25–75%. Colletotrichum Falcatum is probably the most destructive sugarcane disease in the region [5]. A few top-notch sugarcane assortments had to be disposed of due to severe red rot pestilences that struck the region during the last century. Additionally, newly discovered variants of the microbe were to blame for the breakdown of safe varieties that had been provided. To a certain extent, the main pathotypes employed in the screening procedure were identified at the morphological, sociological, pathogenicity, serological, genetic, and sub-atomic levels. In addition, phylogenetic analysis using 75 Colletotrichum Falcatum separates based on 5.8 S-ITS revealed the existence of two major groups, comprising 95% separates with detrimental characteristics and one minor group with 5% disengages with least detrimental characteristics. The world's excessive use of sugar is a source of concern for the general public [2]. This is because sugar consumption is increasing daily, especially in agricultural nations where per capita consumption is relatively low. For example, the global demand for sugar is expected to increase to 203 Mt by 2028, which might add 32 Mt to the present weight. 68 countries that produce sugarcane experience the red rot. The http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1435 virus reduces sugarcane production by fifty percent. In any case, differentiating evidence using morphologic methods is insufficient because of the numerous covering qualities within the species' complex. Furthermore, managing red rot infections in the field presents challenges due to the organism's ever-changing inherited appearance. The development of new infectious races is a problem, and there are no commercially viable varieties that offer enough protection against Colletotrichum Falcatum. However, the use of red rot-safe sugarcane varieties [10] can help control this disease to some extent. Despite several fungicides being effective in vitro, their practical application was hindered by the unbreakable concept of stuck skin. Early on in the contamination process, it is difficult to identify the illness in the field since the characteristic red and white patches that eventually develop on the stem are the result of internal tissue flushing. Agricultural activities like weed identification in a field, agricultural product management transport route arrangement, and so forth, take advantage of PC vision strategies [11]. There is a similar hidden approach involved in these strategies. First, using a state-of-the-art camera, computerized photos are taken from the surrounding environment. After that, image processing techniques are used to extract important highlights that are necessary for a closer look at these pictures. After that, a few intelligent selecting techniques, like quantifiable, Bayesian, or neural organizations, may be applied to arrange the pictures in accordance with the specific problem nearby. This includes the overarching concept that serves as the framework for all algorithms related to vision. Many diseases can affect plants, and if a portion of one of these diseases is not identified and treated in a timely manner, it can completely destroy the crop. This may be extremely costly to farmer and lead to decreased production from conventional crops, which would raise prices and put greater pressure on the economy. Therefore, accurate disease recognition is extremely important and necessary to provide basic infection data. Leaf surface images were obtained from the initial RGB photos [12] and then transformed to the L*a*b tone model with the highest compression level. The shading model L*a*b accurately identifies disease, and the results are independent of the camera streak, sort of leaf, foundation, and sickness spot kind. For darker scale images and more effective execution, the K-implies technique is effective. The K-NN classifier is used to organize the obtained highlights. Feature extraction uses a CNN design, [13] which enables the model to extract discriminative characteristics from the images. These traits are then employed to teach a CNN classifier itself, improving the model's capacity to distinguish between different types of disease lessons. The model's performance is assessed through the use of common measures like loss and accuracy on an independent test set. In the sphere of farming, identifying disease in a plant is important [14]. A healthy agricultural system depends on assessing plants health and diagnosing bacterial and viral infections Farmers identify disease with their own eyes, which is especially challenging and involves regular examination of the crop. Additionally, there is a chance that an inaccurate result will occur, and large agricultural land might discover this method unaffordable. In other regions, a farmer might have to travel a considerable distance to get in touch with specialists, which is difficult and expensive. Every time, calling experts for analysis is barely feasible. Unprecedented research is http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1436 being done using image preparation techniques in an effort to provide a quick and easy way to accurately diagnose diseases across the board. These diseases affect the sugarcane's leaves and stems. The images in various formats and patterns are captured in order to identify the diseases. The image is converted to a dim scale image during preprocessing since it takes a long time to identify diseases in shading images. Using K-Means bunching, the image is divided into various regions or groups in the division stage. These groups focus on the image's core features. Basic highlights such as homogeneity, entropy, connection, and so on are found in the highlight extraction process. The extracted highlights are compared with the typical and atypical standard images of infections during the identification process. It is found that whether the image is typical or affected by diseases because of the association. Typically, the microorganism Colletotrichum Falcatum [15] resides as torpid spores in the soil and as dynamic saprophytes on decomposing host plant parts. The management of the red rot infection in the field presents challenges because this parasite's genetic makeup is constantly changing. The red rot disease can be controlled in three main ways: (1) by using a safe assortment; (2) by treating it with fungicides like Carbendazim; and (3) by using adversarial microorganisms for organic management. Even if using safe assortments is a crucial part of managing red rot, the Colletotrichum Falcatum is nevertheless able to thrive in the freshly delivered safe assortments because of the sporadic growth of its more modern variants. Diseases of the sugarcane plant have a broad logical scope and may focus on the organic properties of the illness [19]. Plant disease detection and identification become motivating and require special attention. The discovery of these diseases coincides with a higher level of sugarcane production, which benefits both ranchers and purchasers. To control more significant harm, preventive actions are implemented through early detection of sugarcane illnesses. The traditional method for detecting infections, identifying illnesses, and managing these diseases in sugarcane is physical. For newcomers in the green cycle, a robotized system designed to assist [16] in identifying diseases of plants based on the appearance of the plant and visual indicators could be incredibly beneficial. This might be demonstrated as an essential tool for farmers, alerting them just in time to prevent the disease from spreading throughout the vast region. Another, more recent method with precise results and great potential for data assessment and image handling is deep learning. Deep learning has made its way into the agricultural industry just as it has been successfully implemented in many other fields. Therefore, it might use a substantial sorting method to evaluate robot recognition and representation of plant leaf contaminations. Deep learning has enabled the most significant improvements in picture classification, and these improvements have served as the basis for identifying and managing plant diseases by using technology to identify photos as the foundation for identifying several crop illnesses. [17] This method of comparison can efficiently classify infections of sugarcane leaves Red rot, red rust, yellow, and mosaic using images of leaves. CNNs, or convolutional neural networks, are now among the most widely used deep learning models for image categorization jobs, for example disease assessment in crops. Sugarcane that is susceptible to disease has a direct impact on both the quantity and quality of production [18]. Infections in the sugarcane cause farmers uneasiness, since http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1437 they possess the power to completely destroy a crop area, causing loss of revenue. Researchers are trying to apply methods for AI, such as machine learning (ML) and deep learning (DL) to examine the agricultural data like estimation of production, forecasting of the retail price, quality of the soil, climate, etc. and protect against crop loss because of numerous causes. It is important for farmers who cultivate to be equipped with real-time data analysis with a range of computer strategies in addition to managing large datasets. MATERIALS AND METHODS The Faster R-CNN approach is still important in understanding proposal regions since the concept zones are demonstrated into disease groups by arranging CNNs from beginning to end in the Faster R-CNN approach. The validity is dependent on the illustration of the space idea module. To observe the sugarcane infection image, faster R-CNN does not need to work with the array of same size. As an image input, both width and length should be managed to avoid curving. Following the upgrade of the Regional Proposal Network (RPN), the differentiating proof speed has significantly increased. A joining of the space recommendation computation in a CNN may result in faster execution. The technique is primarily driven by Faster R-CNN to create a single and reliable model that includes RPN and fast R-CNN with shared feature layers. By and large, sugarcane pictures from different areas are used to outline image modules that can be controlled to produce nearly identical infected sugarcane images. Critical standards are employed to examine the small size items that are used to withdraw the unlimited techniques. The multi-objective (MO) features of the actual level sugarcane image are particular type of numerical thought that is generally used for restricting and combining acquired image working systems. Aside from the Faster RCNN, the primary approach is to assess the sign based on scale. It receives a large premium for signal management, numerical assessment, and number shuffle. The suggested solution for detecting sugarcane disease uses a quicker RCNN technique. An RPN is a fully convolutional network that predicts both object bounds and object ness scores for each position. This is accomplished by the use of an info image (adjusted to a specific size). The efficiency of the convolutional layer is determined by the stage of neural organization. Fig 3. Workflow of working model http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1438 Data Collection Each task acknowledged here demonstrates improved results. However, the problem with these studies is that the images were either taken in the research office's controlled setting or acquired from the crop town data collection. This dataset, which is available at https://github.com/The77Lab/SugarcaneDeepLearning/tree/master/HoCP09-804, has 1450 photos of sugarcane with a distinct location that is separated into two groups. These relate to significant diseases that affect crop worldwide. Each image was taken in a same setting with various varieties. The images were shot in different fields for betterment. All of the pictures were taken with professional lenses at different angles, bearings, and the base, covering the majority of the ranges that may be seen in pictures taken in a verified area. The collection of the dataset was carried out in collaboration with professional pathologists. It significantly clarified the dataset by tying the infected areas to the steams (object region) identifying with diseases. The vast majority of the images in the dataset illustrate different contaminated areas of growing models. These imperfections were all automatically fixed using suitable adjustments. Data Preprocessing To improve integrate extraction, images are presented as the dataset for essential neural associations, which were pre-processed to ensure accuracy. To save time, the dataset's images were scaled to 256×256 before being processed in Python using the OpenCV framework. Overfitting occurs in AI, just as it does in bits of knowledge, when a true model represents subjective uproar or confusion rather than a basic relationship. The visual advancement included one of several progress systems, such as relative change, viewpoint change, image unrests, and force transformations. The goal of this technology (Faster RCNN) is to detect and determine the disease classification in an image. It must recognize the item as well as understand the class in which it belongs. Expand the disease area to modify it using various component extractors that detect contamination in the image. There are several variables to consider while selecting a Feature Extractor, such as the number of layers, as a larger number of boundaries increases the complexity of the framework and directly affects its speed and results. Despite the fact that each arrangement was designed with specified qualities, they all serve the same purpose: to increase precision while reducing computing complexity. The framework execution is evaluated initially in terms of Intersection Over-Union (IOU), followed by Average Precision (AP), which has been provided in the Pascal VOC Challenge. The research involved a number of assessment parameters. These include recall (R), precision (P), accuracy (A), area under curve (AUC), detection rate (DR), and F1 score (F1). The rate of detection can be determined by utilizing the formula shown in Eq. 3.1. Detection Rate= TP (TP+FN) (3.1) The AUC can be determined by utilizing the following formula shown in Eq. 3.2. http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1445 Fig 7. Precision Graph The F1 score serves as a comprehensive evaluation of the structure's accuracy and precision. It indicates that the technique under consideration surpasses the current standards, demonstrating a higher level of precision and accuracy. Figure 8 illustrates the detection rates of the various techniques being compared. Fig 8. F1 Score Graph The detection rate is an overall evaluation of the structure in terms of accuracy and precision. The detection rate for the presented approach is higher than that currently exist, indicating that the system is more accurate. Figure 9 depicts the detection rates of the evaluated methodologies. 0.85 0.93 0.8 0.82 0.84 0.86 0.88 0.9 0.92 0.94 Precision Precision Faster-RCNN 0.93 K-NN 0.85 Faster-RCNN K-NN 0.84 0.91 0.8 0.82 0.84 0.86 0.88 0.9 0.92 FI Score FI Score Faster-RCNN 0.91 K-NN 0.84 Faster-RCNN K-NN http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1446 Fig 9. Detection Rate Graph The suggested approach performs well since Faster-RCNN is a Python algorithm that works effectively with images. Disease detection with images is a difficult task. To complete this challenging task, an efficient method is necessary. Faster-RCNN is a highly efficient algorithm for performing this task. CONCLUSION This paper describes Colletotrichum Falcatum disease in sugarcane. There have been various approaches established to detect Colletotrichum Falcatum, the cause of red rot in sugarcane, but there are certain obstacles with diagnosing this disease. This study offered a machine learning-based method for detecting Colletotrichum Falcatum red rot sugarcane disease. The model, 2DFM-AMMF noise reduction, and quicker 2DOtsu segmentation were utilized. The technique employs a pictorial system, i.e., different photographs of sugarcane of varying sizes, to separate features at different scales and detect Colletotrichum Falcaum disease in sugarcane. The experiment demonstrates that the proposed technique is more precise and efficient than the existing techniques. The study also addresses the security of the dataset. To increase efficiency, the proposed technique relies on the most cutting-edge technologies available. It uses the most recent Python libraries to present an exceptional demonstration. It also works on solid data. Different data may have a slight impact on accuracy and AUC. It contains complicated mathematical tasks. Features and picture quality had an impact on the execution of different or fragmented data. The investigation uses NumPy, Pandas, and Matplotlib in this system, which looks to have the best results in terms of feature extraction and dependence checks. These libraries may eventually be replaced by other libraries. Similarly, pointless computation can be combined with ideas for improving disease diagnosis. 0.91 0.96 0.88 0.89 0.9 0.91 0.92 0.93 0.94 0.95 0.96 0.97 Detection Rate Detection Rate Faster-RCNN 0.96 K-NN 0.91 Faster-RCNN K-NN http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1447 REFERENCES Silva, T.C., et al., Dry rot caused by the complex Colletotrichum falcatum and Thielaviopsis paradoxa emerges as a key stalk disorder in newly expanded sugarcane plantations from Northwestern São Paulo, Brazil. Agronomy, 2023. 13(11): p. 2729. Hossain, M.I., et al., Current and prospective strategies on detecting and managing colletotrichumfalcatum causing red rot of sugarcane. Agronomy, 2020. 10(9): p. 1253. Nandakumar, M., et al., Use of green fluorescent protein expressing Colletotrichum falcatum, the red rot pathogen for precise host–pathogen interaction studies in sugarcane. Sugar Tech, 2020. 22: p. 112-121. Huang TiSen, H.T., et al., Detecting sugarcane borer diseases using support vector machine. 2018. Elsharif, A.A. and S.S. Abu-Naser, An expert system for diagnosing sugarcane diseases. International Journal of Academic Engineering Research (IJAER), 2019. 3(3): p. 19-27. Viswanathan, R., et al., Epidemiology of Fusarium diseases in sugarcane: a new discovery of same Fusarium sacchari causing two distinct diseases, wilt and pokkah boeng. Sugar Tech, 2017. 19: p. 638-646. Zakari, B., et al., Effect of Red Rot Pathogen (Colletotrichum falcatum) on the Nutritional Contents of Sugarcane in the Savannah Ecological Zone of Nigeria. BIMA JOURNAL OF SCIENCE AND TECHNOLOGY (25366041), 2024. 8(2A): p. 293-300. Jayakumar, V., A. Ramesh Sundar, and R. Viswanathan, Biocontrol of Colletotrichum falcatum with volatile metabolites produced by endophytic bacteria and profiling VOCs by headspace SPME coupled with GC–MS. Sugar Tech, 2021. 23(1): p. 94-107. Srivastava, S., et al., A novel deep learning framework approach for sugarcane disease detection. SN Computer Science, 2020. 1: p. 1-7. Bukhari, K.A., et al., Detection of Colletotrichum falcatum causing red rot of sugarcane by enzyme-linked immunosorbent assay. Archives of Phytopathology and Plant Protection, 2012. 45(7): p. 823-830. Kumar, S.S. and B. Raghavendra. Diseases detection of various plant leaf using image processing techniques: A review. in 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS). 2019. IEEE. Umapathy Eaganathan, J.S., V. Lackose, and F.J. Benjamin, Identification of sugarcane leaf scorch disease using K-means clustering segmentation and KNN based classification. International Journal of Advances in Computer Science and Technology (IJACST), 2014. 3(12): p. 11-16. Patil, A.P. and M.S. Patil, Automated Identification and Classification of Sugarcane Diseases Using a Machine Learning and Image Analysis. Surianaranayanan, C. and V. Durairaj, Image segmentation using clustering for detection of diseases in sugarcane. International Journal of Pure and Applied Mathematics, 2018. 118(18): p. 2959-2963. Patel, P., et al., Molecular identification and biocontrol activity of sugarcane rhizosphere bacteria against red rot pathogen Colletotrichum falcatum. http://amresearchreview.com/index.php/Journal/about Volume 3, Issue 11 (2025) Online ISSN Print ISSN . . 3007-3197 3007-3189 http://amresearchreview.com/index.php/Journal/about Page 1448 Biotechnology Reports, 2019. 21: p. e00317. Kumar, P., Research Paper On Sugarcane Diseaese Detection Model. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 2021. 12(6): p. 5167-5174. Scientific, L.L., ARTIFICIAL INTELLIGENCE FRAMEWORK FOR MULTICLASS SUGARCANE LEAF DISEASES CLASSIFICATION USING DEEP LEARNING ALGORITHMS. Journal of Theoretical and Applied Information Technology, 2024. 102(10). Upadhye, S.A., M.R. Dhanvijay, and S.M. Patil, Sugarcane disease detection Using CNN-deep learning method: An Indian perspective. Universal Journal of Agricultural Research, 2023. 11(1): p. 80-97. Militante, S.V., B.D. Gerardo, and R.P. Medina. Sugarcane disease recognition using deep learning. in 2019 IEEE Eurasia conference on IOT, communication and engineering (ECICE). 2019. IEEE.