Crop diseases, unfavorable growth, and nutritional deficiencies have a significant impact on the quality and quantity of agricultural income. According to the United Nations’ Food and Agriculture Organization, it is estimated that pre- and post-harvest diseases alone destroy at least 20–40% of global agricultural production. In developing countries like Cambodia, farmers tend to have a limited understanding of crop diseases and how to treat them, therefore AI solutions can assist farmers in detecting crop irregularities and diseases, which are now lacking in the agricultural sector. With the advancement and developments in AI Deep Learning Algorithms, this paper focuses on how disease dataset was collected and generated, as well as experimenting with four CNN models to detect and recognize the disease name across thirteen disease classes and evaluate the model performance such as accuracy, confusion matrix and computing resource consumptions that operate best with this dataset and can be integrated into mobile phone applications and microprocessor devices. The result of this research is a labeled crop disease dataset and experimental results, this dataset can achieve highest accuracy of 89.210%, 90.558%, 92.100%, 91.136% for InceptionV3, InceptionResNetV2, MobileNetV2 and EfficientNetB0, respectively.