Plant diseases are visually observable patterns of a particular plant. Varieties of plant diseases, which are recognized by human beings, are identical or look similar in appearance. In this paper, we have considered recognition of fungal disease symptom like powdery mildew, looking similar in appearance affected on different produce. The powdery mildew symptom affected on produce like grape, mango, chili, wheat, beans and sunflower are considered for classification. Colour and texture features are extracted from image samples of produce affected by powdery mildew symptom. The extracted features are then used as inputs to knowledge-based and artificial neural network (ANN) classifiers and tests are performed to classify image samples. The colour analysis is done using Red, Green, Blue (RGB) and Hue, Saturation, Intensity (HSI) models. Texture analysis is done using gray level co-occurrence matrix (GLCM). The overall average classification accuracy with colour, texture and combined features are 70.48 %, 70.07 % and 76.61 % respectively using the ANN classifier. The overall average classification accuracy has increased to 71.92 %, 80.60 % and 87.80 % with colour, texture and combined features respectively using the knowledge-based classifier.

Cervical cancer is one of the leading causes of mortality among women, emphasizing the need for accurate diagnostic methods particularly in developing countries where access to regular screening is limited. Early detection and accurate classification of cervical cancer stages are crucial for effective treatment and improved survival rates.This study explores the potential of deep learning based convolutional neural networks (CNNs) for classifying cervical cytological images from the Sipahan Kanker Metadata (SIPaKMeD) dataset.The SIPaKMeD dataset originally containing 4,049 images is augmented to 24,294 images to enhance model generalization. We employed VGG-16, EfficientNet-B7, and CapsNet CNN models using transfer learning with ImageNet pretrained weights to improve classification accuracy.The experimental results show that EfficientNet-B7 achieved the average highest classification accuracy of 91.34%, outperforming VGG-16 (86.5%) and CapsNet (81.34%). Evaluation metrics such as precision, recall, and F1-score further validate the robustness of EfficientNet-B7 in distinguishing between different cervical cancer stages. After testing with various hyperparameters, EfficientNet-B7 minimizes misclassification errors and is able to categorize data more accurately compared to other CNN models.These findings highlight the potential of deep learning CNNs for automated cervical cancer diagnosis, aiding doctors in clinical decision-making to classify medical images and diagnose diseases. Consequently, diagnostic accuracy improves, facilitating more effective treatment planning in the healthcare sector.