An improved local binary pattern method for pollen image classification and recognition

Most of the current feature extraction algorithms in pollen images perform recognition by extracting the contour, shape, texture, and spatial and frequency domain features of the divided images. For improving the effect of recognition, the improved Local Binary Pattern method is proposed for pollen image classification and recognition. Firstly, the image features are described by calculating and counting the directional histogram of the image's gradient. Secondly, the obtained image normalization processing result determines and generates corresponding samples, and multi-scale features are performed on the pollen images. Finally, the Histogram of Oriented Gradients are fused and binary coded by Local Binary Pattern method, and the similarity of each image is been calculated using Manhattan Distance. The experimental results use the Correct Recognition Rate and the Average Recognition Time. The experimental results can show that the proposed method is superior to other methods and robust to noise and rotation of pollen images.