Several efforts have been made in finding alternate sources of energy. The production of bio-fuel from the extracts of plants like Jatropha Curcas L. and Pongamia Pinnata L. is most favored among all. But, due to certain biotic factors, the growth of these plants get affected, therefore reducing the overall production. To formulate the demand and automate the disease diagnosis system a Computer vision methodology is proposed in this work. For disease region segmentation, a Hybrid Neural Network incorporated with Superpixel clustering is proposed. Color, shape, and texture features are evaluated using different algorithms. Finally, seven different Machine Learning techniques were used to classify the images among three categories. Segmentation results with average Specificity = 0.9534, 0.9795, Sensitivity = 0.9637, 0.9805 and average Classification accuracy = 0.9857 ± 0.0285, 0.9095 ± 0.0688 and 0.9607 ± 0.0256 for both the plants when evaluated separately proved the supremacy of the proposed work.

在寻找替代能源方面已经做出了一些努力。最受青睐的是从麻风树（Jatropha Curcas L.）和樟子松（Pongamia Pinnata L.）等植物的提取物中生产生物燃料。但是，由于某些生物因素，这些植物的生长受到影响，因此降低了总产量。为了制定需求和使疾病诊断系统自动化，本文提出了一种计算机视觉方法。对于疾病区域分割，提出了一种结合了超像素聚类的混合神经网络。颜色，形状和纹理特征使用不同的算法进行评估。最后，使用七种不同的机器学习技术将图像分类为三个类别。细分结果的平均特异性= 0.9534，0.9795，灵敏度= 0.9637，0。