Computer Analysis of Images and Patterns: 19th International Conference, Caip 2021, Virtual Event, September 28-30, 2021, Proceedings, Part I

ISBN-13: 9783030891275 / Angielski / Miękka / 2021 / 524 str.

Tsapatsoulis, Nicolas

Opis

The two volume set LNCS 13052 and 13053 constitutes the refereed proceedings of the 19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021, held virtually, in September 2021. The 87 papers presented were carefully reviewed and selected from 129 submissions. The papers are organized in the following topical sections across the 2 volumes: 3D vision, biomedical image and pattern analysis; machine learning; feature extractions; object recognition; face and gesture, guess the age contest, biometrics, cryptography and security; and segmentation and image restoration.

Spis treści

3D Vision.- Simultaneous Bi-Directional Structured Light Encoding for Practical Uncalibrated Profilometry.- Joint Global ICP for Improved Automatic Alignment of Full Turn Object Scans.- Fast Projector-Driven Structured Light Matching in Sub-Pixel Accuracy using Bilinear Interpolation Assumption.- Pyramidal Layered Scene Inference with Image Outpainting for Monocular View Synthesis.- Out of the Box: Embodied Navigation in the Real World.-Toward a novel LSB-based collusion-secure fingerprinting schema for 3D video.- A Combinatorial Coordinate System for the Vertices in the Octagonal C₄C₈ ( R) Grid.- Bilingual Speech Recognition by Estimating Speaker Geometry from Video Data.- Cost-efficient Color Correction Approach on Uncontrolled Lighting Conditions.- HPA-Net: Hierarchical and Parallel Aggregation Network for Context Learning in Stereo Matching.- MTStereo 2.0: accurate stereo depth estimation via Max-tree matching.- Biomedical Image and Pattern Analysis.- H-OCS: a hybrid optic cup segmentation of retinal images.- Retinal Vessel Segmentation using Blending-based Conditional Generative Adversarial Networks.- U-shaped densely connected Convolutions for Left ventricle segmentation from CMR images.- Deep Learning approaches for Head and Operculum Segmentation in Zebrafish Microscopy Images.- Shape Analysis Approach towards Assessment of Cleft Lip Repair Outcome.- MMEC: Multi-Modal Ensemble Classifier for Protein Secondary Structure Prediction.- Breast Cancer Brain Metastasis: Automated MRI Image Analysis for the Prediction of Primary Cancer Using Radiomics.- An Adaptive Semi-Automated Integrated System for Multiple Sclerosis Lesion Segmentation in Longitudinal MRI Scans Based on a Convolutional Neural Network.- A Three-Dimensional Reconstruction Integrated System for Brain Multiple Sclerosis Lesions.- Rule Extraction in the Assessment of Brain MRI Lesions in Multiple Sclerosis: Preliminary Findings.- Invariant Moments, Textural and Deep features for Diagnostic MR and CT Image Retrieval.- Toward multiwavelet Haar-Schauder entropy for biomedical signal reconstruction.- Machine Learning.- Handling Missing Observations with an RNN-based Prediction-Update Cycle.- eGAN: Unsupervised approach to class imbalance using transfer learning.- Progressive Contextual Excitation for Smart Farming Application.- Fine-Grained Image Classification for Pollen Grain Microscope Images.- Adaptive Style Transfer Using SISR.- Object-Centric Anomaly Detection using Memory Augmentation.- Document Language Classification: Hierarchical Model With Deep Learning Approach.- Parsing Digitized Vietnamese Paper Documents.- EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task.- When Deep Learners Change Their Mind: Learning Dynamics for Active Learning.- Learning to Navigate in the Gaussian Mixture Surface.- A Deep Hybrid Approach For Hate Speech Analysis.- On improving generalization of CNN-based image classification with delineation maps using the CORF push-pull inhibition operator.- Fast Hand Detection in Collaborative Learning Environments.- Assessing the Role of Boundary-level Objectives in Indoor Semantic Segmentation.- Skin lesion classification using convolutional neural networks based on Multi-Features Extraction.- Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing.- Layer-wise Relevance Propagation based Sample Condensation for Kernel Machines.-