Journal of Image Processing & Pattern Recognition Progress

Journal of Image Processing & Pattern Recognition Progress Journal of Image Processing & Pattern Recognition Progress [2394-1995(e)] is a peer-reviewed hybrid open-access journal launched in 2014 focused on the rapid publication of fundamental research papers on all areas of Image Processing & Pattern Recognition.

• Image representation and transforms: discrete Fourier, cosine, Walsh, and Hadamard transforms, wavelet, ridgelet, and curvelet representations, Karhunen–Loève and principal component representations, sparse and dictionary-based representations, graph signal processing on images, and multiscale analysis.
• Image enhancement and restoration: denoising under Gaussian, speckle, and impulse noise, deblurring and deconvolution, inpainting and image completion, total variation and regularised inverse problems, super-resolution, contrast and colour correction, and learned restoration priors.
• Image and video coding: transform and predictive coding, vector and scalar quantisation, entropy and Huffman coding, fractal and region-based coding, rate–distortion optimisation, perceptual and masking-based coding, and learned image compression.
• Image segmentation: thresholding, region growing, and clustering-based methods, edge and contour detection, active contours and level sets, graph-based segmentation, semantic and instance segmentation, and evaluation metrics for segmentation quality.
• Feature extraction and representation learning: local and global descriptors, shape, texture, and colour features, keypoint detection and matching, handcrafted versus learned features, dimensionality reduction, and feature selection and fusion strategies.
• Pattern recognition and classification: statistical and structural pattern recognition, clustering and unsupervised learning, kernel methods and ensemble classifiers, extreme learning machines, graph-based and syntactic recognition, classifier evaluation and benchmarking, and handling of imbalanced and limited training data.
• Deep learning for visual analysis: convolutional and transformer architectures for vision, transfer learning and domain adaptation, self-supervised and contrastive learning, recurrent and temporal models for sequences, generative models for image synthesis, model compression for deployment, and interpretability of visual models.
• Object detection and recognition: detection frameworks and region proposals, multi-scale and small-object detection, fine-grained and instance recognition, RGB-D and multimodal recognition, scene understanding and context modelling, and open-set and few-shot recognition.
• Video analysis and tracking: motion estimation and optical flow, single and multiple object tracking, video object segmentation, action and gesture recognition, temporal modelling and event detection, and online and real-time video processing.
• Biometric recognition: fingerprint, face, iris, and handwriting recognition, gait and behavioural biometrics, unimodal and multimodal biometric fusion, template protection and biometric privacy, liveness and spoofing detection, and evaluation of biometric system performance.
• Document analysis and recognition: layout and structure analysis, optical character recognition, handwritten text and digit recognition, script and language identification, key information extraction from complex documents, table and form understanding, and historical document processing.
• Medical and biological image analysis: modality-specific processing for radiological, histopathology, microscopy, and ultrasound images, lesion detection and segmentation, registration of medical images, quantitative imaging biomarkers, and computer-aided diagnosis systems.
• Remote sensing and aerial image analysis: hyperspectral and multispectral image classification, synthetic aperture radar image interpretation, scene classification and land cover mapping, change detection, pixel- and object-based analysis, and fusion of multi-source geospatial imagery.
• Three-dimensional and depth imaging: stereo and multi-view reconstruction, point cloud processing and registration, structured light and LiDAR-based acquisition, depth estimation from single images, and surface and geometric modelling.
• Image security and forensics: digital watermarking and fingerprinting, steganography and steganalysis, tamper detection and image authentication, manipulated and synthetic media detection, and privacy-preserving visual processing.
• Industrial and applied vision systems: automated visual inspection and defect detection, quality control in manufacturing, robotic and embedded vision, driver assistance and traffic scene analysis, and real-time implementation on constrained hardware.