scholarly journals Recognizing Cursive Typewritten Text Using Segmentation-Free System

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Mohammad S. Khorsheed
Keyword(s):  
Feature Extraction ◽  
Feature Vector ◽  
Feature Space ◽  
Recognition System ◽  
Image Feature ◽  
Text Recognition ◽  
Statistical Features ◽  
Free System ◽  
Novel Method ◽  
Image Pixels

Feature extraction plays an important role in text recognition as it aims to capture essential characteristics of the text image. Feature extraction algorithms widely range between robust and hard to extract features and noise sensitive and easy to extract features. Among those feature types are statistical features which are derived from the statistical distribution of the image pixels. This paper presents a novel method for feature extraction where simple statistical features are extracted from a one-pixel wide window that slides across the text line. The feature set is clustered in the feature space using vector quantization. The feature vector sequence is then injected to a classification engine for training and recognition purposes. The recognition system is applied to a data corpus which includes cursive Arabic text of more than 600 A4-size sheets typewritten in multiple computer-generated fonts. The system performance is compared to a previously published system from the literature with a similar engine but a different feature set.

scholarly journals An Efficient Method for Stamps Recognition Using Histogram Moment with Haar Wavelet Sub-bands

2021 ◽  
pp. 3182-3195
Author(s):  
Maha A. Rajab ◽  
Loay E. George
Keyword(s):  
Feature Extraction ◽  
Feature Vector ◽  
Recognition Rate ◽  
Recognition System ◽  
Haar Wavelet ◽  
Insurance Companies ◽  
Statistical Features ◽  
Local Distribution ◽  
Simple Task ◽  
Haar Wavelet Transform

     One major problem facing some environments, such as insurance companies and government institutions, is when a massive amount of documents has to be processed every day. Thus, an automatic stamp recognition system is necessary. The extraction and recognition of a general stamp is not a simple task because it may have various shapes, sizes, backgrounds, patterns, and colors. Moreover, the stamp can be printed on documents with bad quality and rotation with various angles. Our proposed method presents a new approach for the preprocessing and recognition of color stamp images. It consists of four stages, which are stamp extraction, preprocessing, feature extraction, and matching. Stamp extraction is achieved to isolate complex background and remove unwanted data or noise that is surrounding the stamp area. The preprocessing stage is necessary to improve the stamp brightness and eliminate the rotation that occurs during the stamping process. In feature extraction, the extracted information will be representing the desirable feature vector in order to discriminate between stamps using local distribution of statistical features and Haar wavelet with histogram moment. Finally, each extracted feature vector will be saved in the dedicated system database for matching purpose. The test results indicate that the proposed system provides a high recognition rate for two sets of the proposed features (i.e., 99.29% recognition rate for the local distribution of statistical features and 96.01% recognition rate for the Haar wavelet transform with histogram and moment).

Tactile image computation using a feature extraction algorithm

Robotica ◽  
1992 ◽  
Vol 10 (3) ◽  
pp. 241-254
Author(s):  
M. Mehdian
Keyword(s):  
Feature Extraction ◽  
Local Property ◽  
Recognition System ◽  
Image Feature ◽  
Image Size ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm ◽  
Tactile Image ◽  
Feature Values ◽  
Image Computation

SUMMARYA binary tactile image feature extraction algorithm using image primitive notation and perceptrons is presented. The basic image segments are defined as geometric factors by which the image structure is described so that effective feature values such as image shape, image size, perimeter and texture may be extracted on the basis of local image computation. The local property of the tactile image computation is evaluated by the concept called order of the perceptrons and based on this feature extraction algorithm, an efficient tactile image recognition system is realised.

Feature Extraction of Video Using Artificial Neural Network

2017 ◽  
Vol 11 (2) ◽  
pp. 25-40 ◽  
Author(s):  
Yoshihiro Hayakawa ◽  
Takanori Oonuma ◽  
Hideyuki Kobayashi ◽  
Akiko Takahashi ◽  
Shinji Chiba ◽  
...  
Keyword(s):  
Neural Networks ◽  
Feature Extraction ◽  
Image Recognition ◽  
High Performance ◽  
Feature Space ◽  
Middle Layer ◽  
Image Feature ◽  
Consecutive Series ◽  
Form Analysis ◽  
Low Dimensional

In deep neural networks, which have been gaining attention in recent years, the features of input images are expressed in a middle layer. Using the information on this feature layer, high performance can be demonstrated in the image recognition field. In the present study, we achieve image recognition, without using convolutional neural networks or sparse coding, through an image feature extraction function obtained when identity mapping learning is applied to sandglass-style feed-forward neural networks. In sports form analysis, for example, a state trajectory is mapped in a low-dimensional feature space based on a consecutive series of actions. Here, we discuss ideas related to image analysis by applying the above method.

INVARIANT OBJECT RECOGNITION BASED ON A NEURAL NETWORK OF CASCADED RCE NETS

1993 ◽  
Vol 07 (04) ◽  
pp. 815-829 ◽  
Author(s):  
WEI LI ◽  
NASSER M. NASRABADI
Keyword(s):  
Neural Network ◽  
Learning Strategy ◽  
Feature Vector ◽  
Recognition Rate ◽  
Feature Space ◽  
Recognition System ◽  
Coulomb Energy ◽  
Geometrical Shape ◽  
Shape Information ◽  
Shift Rotation

A neural network of cascaded Restricted Coulomb Energy (RCE) nets is constructed for the recognition of two-dimensional objects. A number of RCE nets are cascaded together to form a classifier where the overlapping decision regions are progressively resolved by a set of cascaded networks. Similarities among objects which have complex decision boundaries in the feature space are resolved by this multi-net approach. The generalization ability of an RCE net recognition system, referring to the ability of the system to correctly recognize a new pattern even when the number of learning exemplars is small, is increased by the proposed coarse-to-fine learning strategy. A feature extraction technique is used to map the geometrical shape information of an object into an ordered feature vector of fixed length. This feature vector is then used as an input to the neural network. The feature vector is invariant to object changes such as positional shift, rotation, scaling, illumination variance, variation of camera setup, perspective distortion, and noise distortion. Experimental results for recognition of several objects are also presented. A correct recognition rate of 100% was achieved for both the training and the testing input patterns.

Study of Fingerprint Image Feature Extraction Algorithm

2014 ◽  
Vol 519-520 ◽  
pp. 577-580
Author(s):  
Shuai Yuan ◽  
Guo Yun Zhang ◽  
Jian Hui Wu ◽  
Long Yuan Guo
Keyword(s):  
Feature Extraction ◽  
Recognition System ◽  
Fingerprint Recognition ◽  
Image Feature ◽  
Feature Points ◽  
Orientation Field ◽  
Fingerprint Image ◽  
Image Feature Extraction ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm

Fingerprint image feature extraction is a critical step to fingerprint recognition system, which studies topological structure, mathematical model and extraction algorithm of fingerprint feature. This paper presents system design and realization of feature extraction algorithm for fingerprint image. On the basis of fingerprint skeleton image, feature points including ending points, bifurcation points and singular points are extracted at first. Then false feature points are detected and eliminated by the violent changes of ambient orientation field. True feature points are marked at last. Test result shows that the method presented has good accuracy, quick speed and strong robustness for realtime application.

scholarly journals A Fast Recognition Method for Space Targets in ISAR Images Based on Local and Global Structural Fusion Features with Lower Dimensions

2020 ◽  
Vol 2020 ◽  
pp. 1-21 ◽  
Author(s):  
Hong Yang ◽  
Yasheng Zhang ◽  
Wenzhe Ding
Keyword(s):  
Feature Extraction ◽  
Structural Feature ◽  
Image Recognition ◽  
Recognition Accuracy ◽  
Feature Space ◽  
Image Feature ◽  
Learning Method ◽  
Sample Data ◽  
Low Dimensional ◽  
Space Target

Feature extraction is the key step of Inverse Synthetic Aperture Radar (ISAR) image recognition. However, limited by the cost and conditions of ISAR image acquisition, it is relatively difficult to obtain large-scale sample data, which makes it difficult to obtain target deep features with good discriminability by using the currently popular deep learning method. In this paper, a new method for low-dimensional, strongly robust, and fast space target ISAR image recognition based on local and global structural feature fusion is proposed. This method performs the trace transformation along the longest axis of the ISAR image to generate the global trace feature of the space target ISAR image. By introducing the local structural feature, Local Binary Pattern (LBP), the complementary fusion of the global and local features is achieved, which makes up for the missing structural information of the trace feature and ensures the integrity of the ISAR image feature information. The representation of trace and LBP features in a low-dimensional mapping feature space is found by using the manifold learning method. Under the condition of maintaining the local neighborhood relationship in the original feature space, the effective fusion of trace and LBP features is achieved. So, in the practical application process, the target recognition accuracy is no longer affected by trace function, LBP feature block number selection, and other factors, realizing the high robustness of the algorithm. To verify the effectiveness of the proposed algorithm, an ISAR image database containing 1325 samples of 5 types of space targets is used for experiments. The results show that the classification accuracy of the 5 types of space targets can reach more than 99%, and the recognition accuracy is no longer affected by the trace feature and LBP feature selection, which has strong robustness. The proposed method provides a fast and effective high-precision model for space target feature extraction, which can give some references for solving the problem of space object efficient identification under the condition of small sample data.

Image Feature Extraction of Moment of Inertia Based on Otsu Threshold Segmentation

2013 ◽  
Vol 756-759 ◽  
pp. 3157-3161 ◽  
Author(s):  
Qing Liu ◽  
Li Ming Zhao ◽  
Li Jun Zhang
Keyword(s):  
Feature Extraction ◽  
Binary Image ◽  
Moment Of Inertia ◽  
Image Feature ◽  
Target Area ◽  
Extraction Algorithm ◽  
Extraction Parameter ◽  
Novel Method ◽  
Simple Extraction ◽  
Binary Image Processing

In order to better extract image feature and recognition, a novel feature extraction algorithm of the binary image processing using Otsu combined with normalized moment of inertia (NMI) is put forward. Firstly, the image is processed into binary image and the target area is effectively segmented utilizing Otsu algorithm based on the criteria of maximal variance between-class , secondly, the NMI feature of the binary image is extracted, and finally, the extraction NMI feature is used in image recognition. Experimental results show that NMI feature of the binary image have the ability of anti-geometric distortions (translation, rotation and scaling, TRS), and anti-brightness distortions, the novel method have characteristics of simple extraction approach, little extraction parameter, easy implementation, and strong robustness.

The Research on Image Segmentation Based on the Minimum Error Probability Bayesian Decision Theory

2011 ◽  
Vol 121-126 ◽  
pp. 1151-1155
Author(s):  
Zhi Yuan Chen ◽  
Gang Luo ◽  
Zhi Gen Fei
Keyword(s):  
Image Segmentation ◽  
Em Algorithm ◽  
Mixture Model ◽  
Error Probability ◽  
Feature Space ◽  
Image Feature ◽  
Bayesian Decision ◽  
Minimum Error ◽  
Novel Method ◽  
Image Edge

The image segmentation technology has been extensively applied in many fields. As the foundation of image identification, the effective image segmentation plays a significant role during the course of subsequent image processing. Many theories and methods have been presented and discussed about image segmentation, such as K-means and fuzzy C-means methods, method based on regions information, method based on image edge detection, etc. In this work, it is proposed to apply Bayesian decision-making theory based on minimum error probability to gray image segmentation. The approach to image segmentation can guarantee the segmentation error probability minimum, which is generally what we desire. On the assumption that the gray values accord with the probability distribution of Gaussian finite mixture model in image feature space, EM algorithm is used to estimate the parameters of mixture model. In order to improve the convergence speed of EM algorithm, a novel method called weighted equal interval sampling is presented to obtain the contracted sample set. Consequently, the computation burden of EM algorithm is greatly reduced. The final experiments demonstrate the feasibility and high effectiveness of the method.

An investigation into machine pattern recognition based on time-frequency image feature extraction using a support vector machine

2010 ◽  
Vol 224 (4) ◽  
pp. 981-994 ◽  
Author(s):  
H Li ◽  
P Zhou ◽  
Z Zhang
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Working Conditions ◽  
Signal Analysis ◽  
Feature Vector ◽  
Rolling Bearing ◽  
Image Feature ◽  
Small Samples ◽  
Support Vector ◽  
Time Frequency

In this article, a new method of pattern recognition for machine working conditions is presented that is based on time-frequency image (TFI) feature extraction and support vector machines (SVMs). In this study, the Hilbert time-frequency spectrum (HTFS) is used to construct TFIs because of its good performance in non-stationary and non-linear signal analysis. Cyclostationarity signal analysis is a pre-processing method for improving the performance of the HTFS in the construction of TFIs. Feature extraction for TFIs is investigated in detail to construct a feature vector for pattern recognition. Gravity centre and information entropy of TFIs are used to construct the feature vector for pattern recognition. SVMs are used for different working conditions classification by the constructed feature vector because of its powerful performance even for small samples. In the end, rolling bearing pattern recognition is used as an example to testify the effectiveness of this method. According to the result analysis, it can be concluded that this method will contribute to the development of preventative maintenance.

Sign in / Sign up

Export Citation Format

Share Document