Automatic modulation recognition of radiation source signals based on two-dimensional data matrix and improved residual neural network

Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper.First,the time series of the radiation source signals are reconstructed into two-dimensional data matrix,which greatly simplifies the signal preprocessing process.Second,the depthwise convolution and large-size convolutional kernels based residual neural network(DLRNet)is proposed to improve the feature extraction capability of the AMR model.Finally,the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type.Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method.The recognition accuracy of the proposed method maintains a high level greater than 90% even at -14 dB SNR.

Blind Recognition of Non-Binary LDPC Codes Based on Ant Colony Optimization

This paper introduces a novel blind recognition of non-binary low-density parity-check(LDPC)codes without a candidate set,using ant colony optimization(ACO)algorithm over additive white Gaussian noise(AWGN)channels.Specifically,the scheme that effectively combines the ACO algorithm and the non-binary elements over finite fields is proposed.Furthermore,an improved,simplified elitist ACO algorithm based on soft decision reliability is introduced to recognize the parity-check matrix over noisy channels.Simulation results show that the recognition rate continuously increases with an increased signalto-noise ratio(SNR)over the AWGN channel.

Statistical Recognition Method of Binary BCH Code

In this paper, a statistical recognition method of the binary BCH code is proposed. The method is applied to both primitive and non-primitive binary BCH code. The block length is first recognized based on the cyclic feature under the condition of the frame length known. And then candidate polynomials are achieved which meet the restrictions. Among the candidate polynomials, the most optimal polynomial is selected based on the minimum rule of the weights sum of the syndromes. Finally, the best polynomial was factorized to get the generator polynomial recognized. Simulation results show that the method has strong capability of anti-random bit error. Besides, the algorithm proposed is very simple, so it is very practical for hardware im-plementation.

An Efficient Bar Code Image Recognition Algorithm for Sorting System

In the sorting system of the production line,the object movement,fixed angle of view,light intensity and other reasons lead to obscure blurred images.It results in bar code recognition rate being low and real time being poor.Aiming at the above problems,a progressive bar code compressed recognition algorithm is proposed.First,assuming that the source image is not tilted,use the direct recognition method to quickly identify the compressed source image.Failure indicates that the compression ratio is improper or the image is skewed.Then,the source image is enhanced to identify the source image directly.Finally,the inclination of the compressed image is detected by the barcode region recognition method and the source image is corrected to locate the barcode information in the barcode region recognition image.The results of multitype image experiments show that the proposed method is improved by 5+times computational efficiency compared with the former methods,and can recognize fuzzy images better.

Recognition of Partially Occluded Objects Based on Segmentation by Median Filtering of Extended Direction Code

The image contour is segmented into lines, arcs and smooth curves by median filtering of extended direction code. Based on this segmentation, a set of new local invariant features are proposed to recognize partially occluded objects, which is more reasonable compared with conventional corner features. The matching results of some typical examples shows that these features are robust ,effective in recognition.

Palmprint Recognition Based on Statistical Local Binary Orientation Code

A novel coding based method named as local binary orientation code （LBOCode） for palmprint recognition is proposed. The palmprint image is firstly convolved with a bank of Gabor filters, and then the orientation information is attained with a winner-take-all rule. Subsequently, the resulting orientation mapping array is operated by uniform local binary pattern. Accordingly, LBOCode image is achieved which contains palmprint orientation information in pixel level. Further we divide the LBOCode image into several equal-size and nonoverlapping regions, and extract the statistical code histogram from each region independently, which builds a global description of palmprint in regional level. In matching stage, the matching score between two palmprints is achieved by calculating the two spatial enhanced histograms＇ dissimilarity, which brings the benefit of computational simplicity. Experimental results demonstrate that the proposed method achieves more promising recognition performance compared with that of several state-of-the-art methods.

Code generation and recognition using a modified ejection system in die-casting process

A code-generation and recognition technology that uses a modified ejection system in the diecasting process is presented.To achieve the highest level of quality management,the first requirement in the manufacturing process is to establish a product management system according to the specific product unit.Thus,a method to individually identify each product,such as a barcode or QR code,is required during the production process.Products manufactured in the die-casting process always have ejector pin(EP)marks.Herein,an ejection system was modified to generate a unique code using EP marks.This ejection system has two features:an EP with a modified head to show the direction of rotation,and a function to dependently rotate EPs(five or six EPs)with a constant angle.The EPs are numbered according to the rotation angle.Thus,the EP marks can be viewed as a five-or six-digit code.A program was also developed to individually identify the products by automatically detecting and reading the EPs using deep learning-based object detection and classification technology.

Face Recognition Using Chain Codes

Face recognition is an active area of biometrics. This study investigates the use of Chain Codes as features for recognition purpose. Firstly a segmentation method, based on skin color model was applied, followed by contour detection, then the chain codes of the contours were determined. The first difference of chain codes were calculated since the latter is invariant to rotation. The features were calculated and stored in a matrix. Experiments were performed using the University of Essex Face database, and results show a recognition rate of 95% with this method, when compared with Principal Components Analysis (PCA) giving 87.5% recognition rate.

A Codebook Design Method for Robust VQ-Based Face Recognition Algorithm

In this paper, we present a theoretical codebook design method for VQ-based fast face recognition algorithm to im-prove recognition accuracy. Based on the systematic analysis and classification of code patterns, firstly we theoretically create a systematically organized codebook. Combined with another codebook created by Kohonen’s Self-Organizing Maps (SOM) method, an optimized codebook consisted of 2×2 codevectors for facial images is generated. Experimental results show face recognition using such a codebook is more efficient than the codebook consisted of 4×4 codevector used in conventional algorithm. The highest average recognition rate of 98.6% is obtained for 40 persons’ 400 images of publicly available face database of AT&T Laboratories Cambridge containing variations in lighting, posing, and expressions. A table look-up (TLU) method is also proposed for the speed up of the recognition processing. By applying this method in the quantization step, the total recognition processing time achieves only 28 msec, enabling real-time face recognition.

Research on Recognition Technology of 2-Dimensional Barcode

This paper briefly introduces the characteristics and structure of symbol QR two-dimensional code, a detailed analysis of the image processing method to identify QR code of the whole process, and the bilinear mapping method is applied to image correction, the final steps of decoding are given. The actual test results show that, the design algorithm has theoretical and practical, this recognition system can correctly read QR code, and has high recognition rate and recognition speed, has practical value and application prospect.

Performance analysis and code recognition for dual N-ary orthogonal hybrid modulation systems

A dual N-ary orthogonal hybrid modulation system is introduced in this paper, which can increase the data rate greatly compared with conventional N-ary orthogonal spread spectrum system, so it can be used for high rate data communication. Then, three code recognition algorithms are presented for dual N-ary orthogonal hybrid modulation system and the analytic bit error rate （BER） performance of the system in additive white Gaussian noise （AWGN） and fiat Rayleigh fading channel is derived. Finally, the computer simulation of the system with three code recognition algorithms is performed, which shows that the simplified maximum a posteriori （MAP） algorithm is the best for the system with a compromise between the performance and the complexity.

SAR IMAGE RECOGNITION BASED ON MULTI-ASPECT OF SHADOW INFORMATION

The traditional synthetic aperture radar（SAR） image recognition techniques focus on the electro magnetic （EM） scattering centers, ignoring the important role of the shadow information on the SAR image recognition. It is difficult to classify targets by the shadow information independently, because the shadow shape is dependent on the radar aspect angle, the depression angle and the resolution. Moreover, the shadow shapes of different targets are similar. When the multiple SAR images of one target from different aspects are available, the performance of the target recognition can be improved. Aimed at the problem, a multi-aspect SAR image recognition technique based on the shadow information is developed. It extracts shadow profiles from SAR images, and takes chain codes as the feature vectors of targets. Then, feature vectors on multiple aspects of the same target are combined with feature sequences, and the hidden Markov model （HMM） is applied to the feature sequences for the target recognition. The simulation result shows the effectiveness of the method.

Human interaction recognition based on sparse representation of feature covariance matrices

A new method for interaction recognition based on sparse representation of feature covariance matrices was presented.Firstly,the dense trajectories(DT)extracted from the video were clustered into different groups to eliminate the irrelevant trajectories,which could greatly reduce the noise influence on feature extraction.Then,the trajectory tunnels were characterized by means of feature covariance matrices.In this way,the discriminative descriptors could be extracted,which was also an effective solution to the problem that the description of the feature second-order statistics is insufficient.After that,an over-complete dictionary was learned with the descriptors and all the descriptors were encoded using sparse coding(SC).Classification was achieved using multiple instance learning(MIL),which was more suitable for complex environments.The proposed method was tested and evaluated on the WEB Interaction dataset and the UT interaction dataset.The experimental results demonstrated the superior efficiency.

Silhouettes Based Human Action Recognition in Video via Procrustes Analysis and Fisher Vector Coding

This paper proposes a framework for human action recognition based on procrustes analysis and Fisher vector coding(FVC).Firstly,we applied a pose feature extracted from silhouette image by employing Procrustes analysis and local preserving projection(LPP).Secondly,the extracted feature can preserve the discriminative shape information and local manifold structure of human pose and is invariant to translation,rotation and scaling.Finally,after the pose feature was extracted,a recognition framework based on FVC and multi-class supporting vector machine was employed to classify the human action.Experimental results on benchmarks demonstrate the effectiveness of the proposed method.

Maximum two-dimensional (u×v,4,1,3)-OOCs

Let Ф（u ×v, k, Aa, Ac） be the largest possible number of codewords among all two- dimensional （u ×v, k, λa, λc） optical orthogonal codes. A 2-D （u× v, k, λa, λ）-OOC with Ф（u× v, k, λa, λc） codewords is said to be maximum. In this paper, the number of codewords of a maximum 2-D （u × v, 4, 1, 3）-OOC has been determined.

Robust Speech Recognition System Using Conventional and Hybrid Features of MFCC,LPCC,PLP,RASTA-PLP and Hidden Markov Model Classifier in Noisy Conditions

In recent years, the accuracy of speech recognition (SR) has been one of the most active areas of research. Despite that SR systems are working reasonably well in quiet conditions, they still suffer severe performance degradation in noisy conditions or distorted channels. It is necessary to search for more robust feature extraction methods to gain better performance in adverse conditions. This paper investigates the performance of conventional and new hybrid speech feature extraction algorithms of Mel Frequency Cepstrum Coefficient (MFCC), Linear Prediction Coding Coefficient (LPCC), perceptual linear production (PLP), and RASTA-PLP in noisy conditions through using multivariate Hidden Markov Model (HMM) classifier. The behavior of the proposal system is evaluated using TIDIGIT human voice dataset corpora, recorded from 208 different adult speakers in both training and testing process. The theoretical basis for speech processing and classifier procedures were presented, and the recognition results were obtained based on word recognition rate.

Recognition of vertical vowel graphemes of Korean characters based on combination of vowel graphemes

Korean characters consist of 2 dimensional distributed consonantal and vowel graphemes. The purpose of reducing the 2 dimensional characteristics of Korean characters to linear arrangements at early stage of character recognition is to decrease the complexity of following recognition task. By defining the identification codes for the vowel graphemes of Korean characters, the rules for combination of vowel graphemes are established, and a recognition algorithm based on the rules for combination of vowel graphemes, is therefore proposed for vertical vowel graphemes. The algorithm has been proved feasilbe through demonstrating simulations.

Human Mouth-State Recognition Based on Image Warping and Sparse Representation Combined with Homotopy

It is often necessary to recognize human mouth-states for detecting the number of audio sources and improving the speech recognition capability of an intelligent robot auditory system. A human mouth-state recognition method based on image warping and sparse representation( SR) combined with homotopy is proposed.Using properly warped training mouth-state images as atoms of the overcomplete dictionary overcomes the impact of the diversity of the mouths' scales,shapes and positions so that further improvement of the robustness can be achieved and the requirement for a large number of training samples can be relieved. The homotopy method is employed to compute the expansion coefficients effectively,i. e.,for sparse coding. The orthogonal matching pursuit( OMP) is also tested and compared with the homototy method. Experimental results and comparisons with the state-of-the-art methods have proved the effectiveness of the proposed approach.

ISAR target recognition based on non-negative sparse coding

Aiming at technical difficulties in feature extraction for the inverse synthetic aperture radar （ISAR） target recognition, this paper imports the concept of visual perception and presents a novel method, which is based on the combination of non-negative sparse coding （NNSC） and linear discrimination optimization, to recognize targets in ISAR images. This method implements NNSC on the matrix constituted by the intensities of pixels in ISAR images for training, to obtain non-negative sparse bases which characterize sparse distribution of strong scattering centers. Then this paper chooses sparse bases via optimization criteria and calculates the corresponding non-negative sparse codes of both training and test images as the feature vectors, which are input into k neighbors classifier to realize recognition finally. The feasibility and robustness of the proposed method are proved by comparing with the template matching, principle component analysis （PCA） and non-negative matrix factorization （NMF） via simulations.

A SPEECH RECOGNITION METHOD USING COMPETITIVE AND SELECTIVE LEARNING NEURAL NETWORKS

On the basis of asymptotic theory of Gersho, the isodistortion principle of vector clustering was discussed and a kind of competitive and selective learning method (CSL) which may avoid local optimization and have excellent result in application to clusters of HMM model was also proposed. In combining the parallel, self organizational hierarchical neural networks (PSHNN) to reclassify the scores of every form output by HMM, the CSL speech recognition rate is obviously elevated.