Multi-component attention-based convolution network for color difference recognition with wavelet entropy strategy

The recognition of color differences in solar cells with complex textures is a significant challenge in cell manufacturing. Traditional methods fail to detect the color difference effectively. Deep learning models have exhibited promise in many engineering fields. A multi-component attention-based convolution approach is proposed for the surface inspection based on the feature information in different color spaces. Wavelet entropy is employed to represent the information of different components, remove redundant components and extract effective feature information. Additionally, a residual attention mechanism is developed to capture local features with contextual semantic information. The best network structure is determined by evaluating the layer depth of the basic model and convolution kernel size. A multi-component network model is constructed based on the formed structure to improve the ability to distinguish different color difference features. Experimental results indicated that the proposed approach exhibits competitive performance. The research solution provides guidance for applications of deep learning to improve the quality of solar cells in manufacturing.