While urad bean is an important grain crop in several locations, it is frequently plagued by a number illness that has a devastating effect on harvest yields and quality. Using Convolutional Neural Net- works (CNNs) with 50 Layers, Local Binary Pattern and Support Vector Machines (SVMs), we offer a deep learning-based method for accurately recognising and categorising disorders of leaves in black gram plants. To begin, we amassed a database of pictures of black gram leaves affected by diseases like leaf blight, leaf spot, and yellow mosaic virus. We did some preliminary processing to clean up the photographs and make them look better. Then, we educated a convolutional neural network model to use to reduce the number of parameters and the LBP used to extract disease classification features from the plant images. Our model’s accuracy was enhanced by employing SVM as a classifier on the CNN50 with LBP model’s outputs features. We were able to decrease the amount of incorrect classifications by using the SVM model to boost classification precision. Using criteria like accuracy, precision, recall, and F1-score, we analysed how well our method performed. Our experiments demonstrate indicates the suggested method executes better than earlier state-of-the- art methods with a degree of 98.69%. In conclusion, we show that deep learning methods, specifically CNN and SVM, may be used to precisely detect and categorise black gram plant leaf diseases. This method may help producers better detect and combat plant illnesses, which would ultimately boost food production and quality.