Insect Recognition Method With Strong Anti-Interference Capability for Next-Generation Consumer Imaging Technology

Consumer electronics products are widely used in the agricultural field, but traditional consumer electronics products are limited to specific environmental applications and are susceptible to external attacks. The next generation of imaging technology is driving the widespread application of electronic consumer products. We propose a novel multi-source visual data fusion insect recognition algorithm called SE-SANet, which has high anti-interference capability and robustness to cope with various attacks in practical applications. Specifically, first, a deep residual contraction network is used to set different thresholds for different samples. Second, a spatial attention mechanism is introduced to assist the model in recognizing image features. When the feature data is input into the attention mechanism, the model filters the features based on their contribution values in spatial locations and ultimately produces the recognition result. The model shows excellent anti-interference ability on our collected dataset of 30 different insects, with a recognition correctness of 93.25%, which is higher than that of the traditional methods Inception-V4, Vgg16, Googlenet, Alexnet, 3.68%, 4.97%, 3.22% and 3.69%, respectively. We propose that the SE-SA model has important research implications in improving the robustness of insect recognition techniques and enhancing the model's anti-interference capability.