Cracks in building facades are inevitable due to the age of the building. Cracks found in the building facade may be further exacerbated if not corrected immediately. Considering the extensive size of some buildings, there is definitely a need to automate the inspection routine to facilitate the inspection process. The incorporation of deep learning technology for the classification of images has proven to be an effective method in many past civil infrastructures like pavements and bridges. There is, however, limited research in the built environment sector. In order to align with the Smart Nation goals of the country, the use of Smart technologies is necessary in the building and construction industry. The focus of the study is to identify the effectiveness of deep learning technology for image classification. Deep learning technology, such as Convolutional Neural Networks (CNN), requires a large amount of data in order to obtain good performance. It is, however, difficult to collect the images manually. This study will cover the transfer learning approach, where image classification can be carried out even with limited data. Using the CNN method achieved an accuracy level of about 89%, while using the transfer learning model achieved an accuracy of 94%. Based on this, it can be concluded that the transfer learning method achieves better performance as compared to the CNN method with the same amount of data input.

Traditional disease detection methods typically depend on visual assessments conducted by human experts, which are time-consuming and subjective. Thus, there is an urgent demand for automated and efficient approaches to accurately detect and classify tea diseases. This study presents an enhanced Real-Time Detection Transformer (RT-DETR), tailored for the accurate and efficient identification of tea diseases in natural environments. The proposed method integrates three novel components: Faster-LTNet, CG Attention Module, and RMT Spatial Prior Block, to significantly improve computational efficiency, feature representation, and detection capabilities. Faster-LTNet employs partial convolution and hierarchical design to optimize computational resources, while the CG Attention Module enhances multi-head self-attention by introducing grouped feature inputs and cascading operations to reduce redundancy and increase attention diversity. The RMT Spatial Prior Block integrates a Manhattan distance-based spatial decay matrix and linear decomposition strategy to improve global and local context modeling, reducing attention complexity. The enhanced RT-DETR model achieves a detection precision of 89.20% and a processing speed of 346.40 FPS. While the precision improves, the FPS value also increases by 109, which is superior to the traditional model in terms of precision and real-time processing. Additionally, compared to the baseline model, the FLOPs are reduced by 50%, and the overall model size and parameter size are decreased by approximately 50%. These findings indicate that the proposed algorithm is well-suited for efficient, real-time, and lightweight agricultural disease detection.