Image and Video Processing and Recognition Based on Artificial Intelligence

© 2022 by the authors; CC BY-NC-ND license

emotion recognition; brain computer interface; bag of deep features; continuous wavelet transform; face image analysis; deep learning; face parsing; facial attributes classification; building extraction; convolutional neural networks; mask R-CNN; high-resolution remote sensing image; deep learning; autoencoders; semi-supervised learning; computer vision; pathology; epidermis; skin; image processing; generative models; generative adversarial net; depth map; super-resolution; guidance; residual network; channel interaction; pose estimation; body orientation; multi-person; multi-task; surface defect detection; active learning; deep learning; generative adversarial network; presentation attack detection; artificial image generation; presentation attack face images; ultrasound image; malignant thyroid nodule; artificial intelligence; deep learning; weighted binary cross-entropy loss; infrared circumferential scanning system; target recognition; deep convolutional neural networks; data augmentation; transfer learning; bounding box regression; loss function; medical image fusion; convolutional neural network; image pyramid; multi-scale decomposition; armature; computer vision; deep learning; surface inspection; action recognition; social robotics; common spatial patterns; vehicle recognition; multi resolution network; optimization; semantic segmentation; global context; local context; fully convolutional networks; image-to-image conversion; image de-raining; label to photos; edges to photos; generative adversarial network (GAN); remote sensing; helicopter footage; deep learning; computer vision; image processing; crowd counting; semantic segmentation; multitask learning; normalized cross-correlation; Marr wavelets; entropy and response; graph matching; RANSAC; deep learning; GC–LSTM model; typhoon; satellite image; prediction system; monocular depth estimation; feature distillation; joint attention; loss function; finger-vein recognition; camera position; finger position; lighting; unobserved database; heterogeneous database; domain adaptation; cycle-consistent adversarial networks; SDUMLA-HMT-DB; HKPolyU-DB; biometrics; face recognition; single-sample face recognition; binarized statistical image features; K-nearest neighbors; sparse coding; fast approximation; homotopy iterative hard thresholding; object recognition; character recognition; orthogonal polynomials; orthogonal moments; Krawtchouk polynomials; Tchebichef polynomials; support vector machine