As part of an effort to develop intelligent agriculture, new methods for enhancing the quality of vegetables are being continually developed. In recent years, the Convolutional Neural Network (CNN) has shown to be the most successful and extensively used approach for identifying the quality of pre-trained vegetables. However, this method is time-consuming due to the scarcity of truly large, significant datasets. Using a pre-trained CNN model as a feature extractor is a straightforward method for utilizing CNNs' capabilities without investing time in training. While, Support Vector Machine (SVM excels at processing data with tiny dimensions and significantly larger instances. SVM more accurately classifies the flatten/vector feature supplied by the CNN fully connected layer with small dimensions. In addition, implementing Data Augmentation (DA) and Weighted Class (WC) for data variety and class imbalance reduction can improve CNN-SVM performance. The research results show highest accuracy during training always achieves 100% across all experimental options. With an average accuracy of 69.66% in the testing process and 92.51% in the prediction process for all data, the experimental findings demonstrate that CNN-SVM outperforms CNN in terms of accuracy performance in all possible experiments, with or without WC and or DA approach.

There are so many different varieties of vegetables in Indonesia that the sorting procedure presents difficulties. In an effort to expedite the introduction of smart farming in Indonesia, more agricultural assistance techniques will be created. Utilizing the Naive Bayes algorithm is one way that may be used to advance agriculture in Indonesia. Image processing consists of converting RGB images to grayscale images, segmenting images using the thresholding method, collecting image features based on the HSV average value and object area, and classifying pictures using the Naive Bayes algorithm. This research seeks to use image processing technologies to agricultural products, particularly vegetables. The system is comprised of a single picture captured by a digital camera. There were eight varieties of vegetables employed for the picture data, with a total of eighty consisting of 64 training data and 16 test data. Spinach, green chilies, red chilies, chayote, cucumber, eggplant, tomatoes, and carrots were the vegetables categorized. The categorization findings indicate that 87.5 % of the test values produced using this approach are accurate. This study demonstrates that the Naive Bayes method has a high degree of accuracy for the categorization of vegetables based on image processing. It is anticipated that the findings of this study would promote the implementation of smart farming 4.0 in Indonesia.