Image Labeling by Integration of Local Co-Occurrence Histogram and Global Features

2014 ◽  
Vol 18 (4) ◽  
pp. 511-517
Author(s):  
Takuto Omiya ◽  
◽  
Kazuhiro Hotta
Keyword(s):  
Posterior Probability ◽  
Probability Distributions ◽  
Texture Features ◽  
Bag Of Words ◽  
Global Features ◽  
Image Labeling ◽  
Local Probability ◽  
Local And Global Features ◽  
Conventional Methods ◽  
Labeling Method

In this paper, we perform image labeling based on the probabilistic integration of local and global features. Several conventional methods label pixels or regions using features extracted from local regions and local contextual relationships between neighboring regions. However, labeling results tend to depend on local viewpoints. To overcome this problem, we propose an image labeling method that utilizes both local and global features. We compute the posterior probability distributions of the local and global features independently, and they are integrated by the product. To compute the probability of the global region (entire image), Bag-of-Words is used. In contrast, local cooccurrence between color and texture features is used to compute local probability. In the experiments, we use the MSRC21 dataset. The result demonstrates that the use of global viewpoint significantly improves labeling accuracy.

Illumination Variant Face Detection System Using Hierarchical Feature Method

2015 ◽  
Vol 764-765 ◽  
pp. 1309-1313
Author(s):  
Chih Hsien Hsia ◽  
Jen Shiun Chiang ◽  
Chin Yi Lin
Keyword(s):  
Detection Rate ◽  
Detection System ◽  
Back Propagation ◽  
Texture Features ◽  
Global Features ◽  
Adaboost Algorithm ◽  
Local And Global Features ◽  
Propagation Network ◽  
Human Faces ◽  
Feature Calculation

In this study, we propose a new solution based on Adaboost algorithm and Back Propagation Network (BPN) of Neural Network (NN) combining local and global features with cascade architecture to detect human faces. We use Modified Census Transform (MCT) feature that belong to texture features and is less sensitive to illumination for local feature calculation. By this approach, it is not necessary to preprocess each sub-window of the image. For classification, we use the structure of hierarchical feature to control the number of features. With only MCT, it is easy to misjudge faces, and therefore in this work we include the brightness information of global features to eliminate the false positive regions. As a result, the proposed approach can have Detection Rate (DR) of 99%, false positives of only 11, and detection speed of 27.92 Frame Per Second (FPS).

On the analysis of local and global features for hyperemia grading

2017 ◽  
Author(s):  
L. Sánchez ◽  
N. Barreira ◽  
N. Sánchez ◽  
A. Mosquera ◽  
H. Pena-Verdeal ◽  
...  
Keyword(s):  
Global Features ◽  
Local And Global Features

scholarly journals Posterior Probability on Finite Set

2012 ◽  
Vol 20 (4) ◽  
pp. 257-263
Author(s):  
Hiroyuki Okazaki
Keyword(s):  
Probability Distribution ◽  
Probability Measure ◽  
Posterior Probability ◽  
Probability Distributions ◽  
Sample Space ◽  
Finite Sample ◽  
Finite Set

Summary In [14] we formalized probability and probability distribution on a finite sample space. In this article first we propose a formalization of the class of finite sample spaces whose element’s probability distributions are equivalent with each other. Next, we formalize the probability measure of the class of sample spaces we have formalized above. Finally, we formalize the sampling and posterior probability.

scholarly journals Methodology for Interactive Labeling of Patched Asphalt Pavement Images Based on U-Net Convolutional Neural Network

2022 ◽  
Vol 14 (2) ◽  
pp. 861
Author(s):  
Han-Cheng Dan ◽  
Hao-Fan Zeng ◽  
Zhi-Heng Zhu ◽  
Ge-Wen Bai ◽  
Wei Cao
Keyword(s):  
Neural Network ◽  
Active Learning ◽  
Convolutional Neural Network ◽  
Sample Size ◽  
Pavement Distress ◽  
Image Labeling ◽  
Gray Area ◽  
Calculation Results ◽  
Labeling Method ◽  
And Training

Image recognition based on deep learning generally demands a huge sample size for training, for which the image labeling becomes inevitably laborious and time-consuming. In the case of evaluating the pavement quality condition, many pavement distress patching images would need manual screening and labeling, meanwhile the subjectivity of the labeling personnel would greatly affect the accuracy of image labeling. In this study, in order for an accurate and efficient recognition of the pavement patching images, an interactive labeling method is proposed based on the U-Net convolutional neural network, using active learning combined with reverse and correction labeling. According to the calculation results in this paper, the sample size required by the interactive labeling is about half of the traditional labeling method for the same recognition precision. Meanwhile, the accuracy of interactive labeling method based on the mean intersection over union (mean_IOU) index is 6% higher than that of the traditional method using the same sample size and training epochs. In addition, the accuracy analysis of the noise and boundary of the prediction results shows that this method eliminates 92% of the noise in the predictions (the proportion of noise is reduced from 13.85% to 1.06%), and the image definition is improved by 14.1% in terms of the boundary gray area ratio. The interactive labeling is considered as a significantly valuable approach, as it reduces the sample size in each epoch of active learning, greatly alleviates the demand for manpower, and improves learning efficiency and accuracy.

scholarly journals Text Sentiment Classification Based on Feature Fusion

2020 ◽  
Vol 34 (4) ◽  
pp. 515-520
Author(s):  
Chen Zhang ◽  
Qingxu Li ◽  
Xue Cheng
Keyword(s):  
Hybrid Model ◽  
Short Term Memory ◽  
Feature Fusion ◽  
Contextual Information ◽  
Sentiment Classification ◽  
Global Features ◽  
Softmax Classifier ◽  
Parallel Hybrid ◽  
Local And Global Features ◽  
Lstm Network

The convolutional neural network (CNN) and long short-term memory (LSTM) network are adept at extracting local and global features, respectively. Both can achieve excellent classification effects. However, the CNN performs poorly in extracting the global contextual information of the text, while LSTM often overlooks the features hidden between words. For text sentiment classification, this paper combines the CNN with bidirectional LSTM (BiLSTM) into a parallel hybrid model called CNN_BiLSTM. Firstly, the CNN was adopted to extract the local features of the text quickly. Next, the BiLSTM was employed to obtain the global text features containing contextual semantics. After that, the features extracted by the two neural networks (NNs) were fused, and processed by Softmax classifier for text sentiment classification. To verify its performance, the CNN_BiLSTM was compared with single NNs like CNN and LSTM, as well as other deep learning (DL) NNs through experiments. The experimental results show that the proposed parallel hybrid model outperformed the contrastive methods in F1-score and accuracy. Therefore, our model can solve text sentiment classification tasks effectively, and boast better practical value than other NNs.

scholarly journals Boosted Vehicle Detection Using Local and Global Features

2013 ◽  
Vol 04 (03) ◽  
pp. 243-252 ◽  
Author(s):  
Chin-Teng Lin ◽  
Sheng-Chih Hsu ◽  
Ja-Fan Lee ◽  
Chien-Ting Yang
Keyword(s):  
Vehicle Detection ◽  
Global Features ◽  
Local And Global Features
Sign in / Sign up

Export Citation Format

Share Document