The identification of plant leaf diseases is crucial in precision agriculture, playing a pivotal role in advancing the modernization of agriculture. Timely detection and diagnosis of leaf diseases for preventive measures significantly contribute to enhancing both the quantity and quality of agricultural products, thereby fostering the in-depth development of precision agriculture. However, despite the rapid development of research on plant leaf disease identification, it still faces challenges such as insufficient agricultural datasets and the problem of deep learning-based disease identification models having numerous training parameters and insufficient accuracy. This paper proposes a plant leaf disease identification method based on improved SinGAN and improved ResNet34 to address the aforementioned issues. Firstly, an improved SinGAN called Reconstruction-Based Single Image Generation Network (ReSinGN) is proposed for image enhancement. This network accelerates model training speed by using an autoencoder to replace the GAN in the SinGAN and incorporates a Convolutional Block Attention Module (CBAM) into the autoencoder to more accurately capture important features and structural information in the images. Random pixel Shuffling are introduced in ReSinGN to enable the model to learn richer data representations, further enhancing the quality of generated images. Secondly, an improved ResNet34 is proposed for plant leaf disease identification. This involves adding CBAM modules to the ResNet34 to alleviate the limitations of parameter sharing, replacing the ReLU activation function with LeakyReLU activation function to address the problem of neuron death, and utilizing transfer learning-based training methods to accelerate network training speed. This paper takes tomato leaf diseases as the experimental subject, and the experimental results demonstrate that: (1) ReSinGN generates high-quality images at least 44.6 times faster in training speed compared to SinGAN. (2) The Tenengrad score of images generated by the ReSinGN model is 67.3, which is improved by 30.2 compared to the SinGAN, resulting in clearer images. (3) ReSinGN model with random pixel Shuffling outperforms SinGAN in both image clarity and distortion, achieving the optimal balance between image clarity and distortion. (4) The improved ResNet34 achieved an average recognition accuracy, recognition precision, recognition accuracy (redundant as it\'s similar to precision), recall, and F1 score of 98.57, 96.57, 98.68, 97.7, and 98.17%, respectively, for tomato leaf disease identification. Compared to the original ResNet34, this represents enhancements of 3.65, 4.66, 0.88, 4.1, and 2.47%, respectively.

Most of the food consumed worldwide is produced by plants. Plant disease is a major cause of reduced production, but can be managed with regular monitoring. Manually observing plant diseases takes more time and is error-prone. Early detection of plant diseases with the aid of artificial intelligence and computer vision can decrease the effects of disease and help plants withstand the downsides of continuing surveillance. In this manuscript, plant disease identification using contextual mask auto-encoder optimized with dynamic differential annealed optimization algorithm (PDI-CMAE-DDAOA) is proposed. The plant village dataset is used to collect the images. Then the image is fed to preprocessing. Using an adaptive self-guided filter approach, the noise is removed from the input images during the pre-processing phase. The result of the pre-processing section serves as input for the feature extraction segment. Four statistical features, including mean, variance, entropy, and kurtosis, are recovered from the cosine similarity hidden Markov model (CSHMM). The contextual mask auto-encoder (CMAE) is given the extracted features to accurately classify the healthy and unhealthy regions of the plant image. The issue of slow convergence affects the CMAE. However, it is noted that the CMAE converges more quickly with deep learning features than with texture features in this instance. The CMAE classifier generally does not exhibit any adaptation of optimization algorithms for determining the best parameters to ensure the precise classification of plant disease. Therefore, dynamic differential annealed optimization algorithm (DDAOA) is considered to enhance the CMAE classifier, which accurately distinguishes between healthy and diseased plants. The proposed PDI-CMAE-DDAOA is done in Python. The efficacy of PDI-CMAE-DDAOA is evaluated under some performance metrics, like accuracy, precision, sensitivity, F1-score, specificity, error rate, receiver operating characteristic curve (ROC), computational time. The proposed method provides higher accuracy 23.34%, 34.33%, and 32.07%; higher sensitivity 36.67%, 36.33%, and 23.21%; higher F1-score 46.67%, 57.56%, and 43.21%; higher specificity 56.67%, 67.56%, and 23.21% analyzed with existing models, like transfer learning-based deep ensemble neural network for plant leaf infection recognition (PDI-DENN), plant disease detection with hybrid model based on convolutional auto-encoder and convolutional neural network (PDI-CAE-CNN), and automatic and reliable leaf disease finding depending on deep learning methods (PDI-EN-CNN), respectively. RESEARCH HIGHLIGHTS: To find the plant disease at early stage. To present PDI-CMAE-DDAOA. To get better classification accuracy by extracting the optimal features with the help of efficient CSHMM. To minimize the error during classification process. To maximize high area under curve value.