Answers are grounded in this paper and cite their sources.
Face recognition is an important identification technology in daily life and one of the research hotspots in the field of computer vision and intelligent image processing. However, many algorithms based on Pulse Coupled Neural Network (PCNN) do not adequately describe features, same parameters are used to process the entire face image, ignoring the difference between the local recognition rate and gray distribution of each part of the face image. This paper proposes a block face recognition algorithm based on the weighted intensity PCNN model, we have refined the description of the features through parameter adaptation, partitioned the face according to the degree of contribution in the recognition process, and set the corresponding weight parameters through the improved grid search algorithm, which can effectively improve the PCNN model's ability to recognize faces. Experiments show that in different face databases, the performance of this model is greatly improved compared with common methods such as PCA and ICA.
No takes yet. Share an insight, caveat, or question.
Deng et al. (2020) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: