30 Result(s)
within
English
Computer Science
Image Processing and Computer Vision
Yu. Li
Chapter
-
Chapter and Conference Paper
An Effective Implementation of a Direct Spanning Tree Representation in GAs
This paper presents an effective implementation based on predecessor vectors of a genetic algorithm using a direct tree representation. The main operations associated with crossovers and mutations can be achie...
-
Chapter and Conference Paper
Data Segmentation of Stereo Images with Complicated Background
With the development of computer science, there is an increasing demand on the object recognition in stereo images. As a binocular image pair contains larger and more complicated information than a monocular i...
-
Chapter and Conference Paper
A Contrast Enhancement Framework with JPEG Artifacts Suppression
Contrast enhancement is used for many algorithms in computer vision. It is applied either explicitly, such as histogram equalization and tone-curve manipulation, or implicitly via methods that deal with degrad...
-
Chapter and Conference Paper
Feature Fusion of Gradient Direction and LBP for Facial Expression Recognition
Feature extraction is an important step in facial expression recognition. A novel method is proposed based on feature fusion which combines gradient direction and LBP features. Firstly, eyes are located throug...
-
Chapter and Conference Paper
Fast Guided Global Interpolation for Depth and Motion
We study the problems of upsampling a low-resolution depth map and interpolating an initial set of sparse motion matches, with the guidance from a corresponding high-resolution color image. The common objectiv...
-
Chapter and Conference Paper
Fault Diagnosis Method of Diesel Engine Based on Improved Structure Preserving and K-NN Algorithm
The diesel engine fault data is nonlinear and it’s difficult to extract the characteristic information. Kernel Principal Component Analysis (KPCA) is used to extract features of nonlinear data, only considerin...
-
Chapter and Conference Paper
A New Scheme for QoE Management of Live Video Streaming in Cloud Environment
Live video streaming process consumes very large data storage and takes very long time, so it requires big data storage and computing infrastructures for implementation. Accordingly, the use of cloud computing...
-
Chapter and Conference Paper
Multi-channel Generative Adversarial Network for Parallel Magnetic Resonance Image Reconstruction in K-space
Magnetic Resonance Imaging (MRI) typically collects data below the Nyquist sampling rate for imaging acceleration. To remove aliasing artifacts, we propose a multi-channel deep generative adversarial network (...
-
Chapter and Conference Paper
L2R-QA: An Open-Domain Question Answering Framework
Open-domain question answering has always being a challenging task. It involves information retrieval, natural language processing, machine learning, and so on. In this work, we try to explore some comparable ...
-
Chapter and Conference Paper
An Advanced Least Squares Twin Multi-class Classification Support Vector Machine for Few-Shot Classification
In classification tasks, deep learning methods yield high performance. However, owing to lack of enough annotated data, deep learning methods often underperformed. Therefore, we propose an advance version of l...
-
Chapter and Conference Paper
Identification of Functional Connectivity Features in Depression Subtypes Using a Data-Driven Approach
Biomarkers are not well understood in depression, partly because there is no golden rule of what is abnormal in which patients and how neurobiological information can be used to improve diagnosis. The heteroge...
-
Chapter and Conference Paper
Data Augmentation for Deep Learning of Judgment Documents
With the increasing number of machine learning parameters, the requirements on data quantity are getting higher and higher to train a good model. The choice of methods and the optimization of parameters can im...
-
Chapter and Conference Paper
Using Case Facts to Predict Penalty with Deep Learning
With the promotion of Wisdom Court construction and the increasing completeness of judicial big data, the combination of judicial and artificial intelligence attracted more and more attention. The Judicial doc...
-
Chapter and Conference Paper
Adaptive Flower Pollination Algorithm Based on Chaotic Map
Flower pollination algorithm (FPA) is one of the well-known evolutionary techniques used extensively to solve optimization problems. Despite its efficiency and wide use, the identical search behaviors may lead...
-
Chapter and Conference Paper
Fast Video Object Segmentation Using the Global Context Module
We developed a real-time, high-quality semi-supervised video object segmentation algorithm. Its accuracy is on par with the most accurate, time-consuming online-learning model, while its speed is similar to th...
-
Chapter and Conference Paper
The Devil Is in Classification: A Simple Framework for Long-Tail Instance Segmentation
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO. They tend to suffer perfor...
-
Chapter and Conference Paper
Learning Infant Brain Developmental Connectivity for Cognitive Score Prediction
During infancy, the human brain develops rapidly in terms of structure, function and cognition. The tight connection between cognitive skills and brain morphology motivates us to focus on individual level cogn...
-
Chapter and Conference Paper
Research on Chinese Word Segmentation Based on Conditional Random Fields
Word segmentation is the first step in Chinese natural language processing. The accuracy of segmentation has substantial impacts on subsequent tasks such as part-of-speech tagging, semantic analysis, etc. This...
-
Chapter and Conference Paper
Chinese Word Sense Disambiguation Based on Classification
Word sense disambiguation (WSD) is a well-known task in the field of natural language processing. It attempts to determine a meaning of a word that has a couple of senses. This paper studies the Chinese word s...
-
Chapter and Conference Paper
Multiple Security Protection Algorithm for GF-2 Images Based on Commutative Encryption and Watermarking
In the process of storage, transmission and use of GF-2 image, both data security transmission and data copyright protection should be considered. The combination of cryptography and digital watermarking is an...
