Robert Hudec

2D-3D Face Recognition Method Basedon a Modified CCA-PCA Algorithm

This paper presents a proposed methodology for face recognition based on an information theory approach to coding and decoding face images. In this paper, we propose a 2D-3D face-matching method based on a principal component analysis (PCA) algorithm using canonical correlation analysis (CCA) to learn the mapping between a 2D face image and 3D face data. This method makes it possible to match a 2D face image with enrolled 3D face data. Our proposed fusion algorithm is based on the PCA method, which is applied to extract base features. PCA feature-level fusion requires the extraction of different features from the source data before features are merged together. Experimental results on the TEXAS face image database have shown that the classification and recognition results based on the modified CCA-PCA method are superior to those based on the CCA method. Testing the 2D-3D face match results gave a recognition rate for the CCA method of a quite poor 55% while the modified CCA method based on PCA-level fusion achieved a very good recognition score of 85%.

Simple comparison of image segmentation algorithms based on evaluation criterion

In the image analysis, image segmentation is the operation that divides image into set of different segments. The paper deals about common color image segmentation techniques and methods. The advantages and disadvantage of each one will be described in this paper. At the end of the paper, the evaluation criterion will be introduced and applied on the algorithms results. Five most used image segmentation algorithms, namely, Efficient graph based, K-means, Mean shift, Expectation maximization and hybrid method are compared by designed criterion.

Face recognition on FERET face database using LDA and CCA methods

This paper provides an example of the 2D face recognition using existing LDA method and our proposed method based on CCA. LDA is a popular feature extraction technique for face recognition. Likewise, the CCA as a novel method is applied to image processing and biometrics too. CCA is a powerful multivariate analysis method and for that case it was applied on faces recognition. In the paper, a proposed methodology for face recognition based on information theory approach of coding and decoding the face image is presented. Developed algorithm has been tested on 20 subjects from FERET database. Test results gave a recognition rate for LDA method quite the good recognition rate 100% respectively 83% for a small number of input subjects 5 respectively 10. For a large number of inputs images is recognition rate very poor about 40% For our proposed CCA method is average recognition rate about 99% for FERET face database.

An Advanced Approach to Extraction of Colour Texture Features Based on GLCM

This paper discusses research in the area of texture image classification. More specifically, the combination of texture and colour features is researched. The principle objective is to create a robust descriptor for the extraction of colour texture features. The principles of two well-known methods for grey-level texture feature extraction, namely GLCM (grey-level co-occurrence matrix) and Gabor filters, are used in experiments. For the texture classification, the support vector machine is used. In the first approach, the methods are applied in separate channels in the colour image. The experimental results show the huge growth of precision for colour texture retrieval by GLCM. Therefore, the GLCM is modified for extracting probability matrices directly from the colour image. The method for 13 directions neighbourhood system is proposed and formulas for probability matrices computation are presented. The proposed method is called CLCM (colour-level co-occurrence matrices) and experimental results show that it is a powerful method for colour texture classification.

The comparison of CPU time consumption for image processing algorithm in Matlab and OpenCV

In order to fill gap of growing demand for high efficient image and video processing, open source computer vision library (OpenCv) is way to deals with this task. Hence, this paper is about basic algorithm for image processing and their CPU time consumption in Matlab comparing with OpenCv. Algorithms are tested on images with resolution 3264×2448, 1920×1080, 1024×768 and 220×260. Multi-processors computer and multi-threading programs are used to improve processing efficiency.

A comparison of key-point descriptors for the stereo matching algorithm

In this paper, the comparison of a novel key-point image descriptors such as DAISY, BRISK, A-KAZE and LATCH with the well-known SIFT and SURF descriptors are tested and compared for the stereo matching algorithm. The main idea of this paper is to present an independent, comparative study and some of the benefits and drawbacks of these most popular image descriptors on stereo images. These descriptors are the primary input for the image correspondence algorithm (stereo matching algorithm). On this assumption, it is possible to estimate depth information from two stereo images. Two sets of experiments are conducted for relative performance evaluations. In the first part of our experiments, the accuracy of stereo matching algorithm using descriptors is demonstrated. The overall time execution is evaluated in the second set of our experiments. The all experiments have been tested on Middlebury stereo-dataset using programming language Python. The experimental result shows that the DAISY descriptor provides better results as A-KAZE or LATCH. On the other hand, DAISY descriptor is slower than SURF. The algorithm based on a DAISY descriptor is effective for matching stereo image pair and these correspondences can be used as input for 3D reconstruction.

Automatic extraction of non-textual information in web document and their classification

This paper deals with research in the area of automatic extraction of textual and non-textual information and their classification. The main idea is to create a robust method for extraction of image and textual segments to obtain short web document. Thus, developed method consist of two data types extractions, where both image and text data extraction are using Document Object Model tree. Extracted objects are saved in separate databases followed the images analysis that define and describe image object from semantic point of view. Moreover, the semantic description of all modal objects are utilized to short web document creation. To accurate object classification, the fast and powerful hybrid segmentation algorithm based on Mean Shift and Believe Propagation principles are mentioned in this paper, too. Likewise, the image segmentation algorithm was integrated with SIFT descriptor. Finally, in order to obtain a semantic description of objects in static image, the SVM classification is used. The developed method was tested on real unsegmented and segmented images, too.

3D image reconstruction from 2D CT slices

In this paper, a 3D reconstruction algorithm using CT slices of human pelvis is presented. We propose the method for 3D image reconstruction that is based on a combination of the SURF (Speeded-Up Robust Features) descriptor and SSD (Sum of Squared Differences) matching algorithm using image segmentation with aim to obtain accurate 3D model of human pelvis. Firstly, we apply image filtering for noise removing and smoothing. Next, the filtered image is split into segments using Mean- Shift segmentation algorithm. Secondly, the edges using Canny edge detector are extracted. Then, for each segment we look at the associated corresponding points. The best corresponding points of all the segments using SURF-SSD method were obtained. The smaller is the value of SSD at a particular pixel, the more similarity exists between the first image and the second image in the neighborhood of that pixel. Finally, we have integrated the Mean-Shift segmentation algorithm with the SURF-SSD method. The obtained experimental results demonstrate that the SURF-SSD algorithm in combination with image segmentation provides accurate 3D model of human pelvis.

Accurate wild animal recognition using PCA, LDA and LBPH

In this paper, the performances of image recognition methods such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Local Binary Patterns Histograms (LBPH) are tested and compared for the image recognition of the input animal images. The main idea of this paper is to present an independent, comparative study and some of the benefits and drawbacks of these most popular image recognition methods. Two sets of experiments are conducted for relative performance evaluations. In the first part of our experiments, the recognition accuracy of PCA, LDA and LBPH is demonstrated. The overall time execution for animal recognition process is evaluated in the second set of our experiments. We conduct tests on created animal database. The all algorithms have been tested on 300 different subjects (60 images for each class). The experimental result shows that the PCA features provide better results as LDA and LBPH for large training set. On the other hand, LBPH is better than PCA and LDA for small training data set.

Feature extraction for object recognition using PCA-KNN with application to medical image analysis

This paper provides a new feature extraction method for object recognition using PCA-KNN algorithm with SIFT descriptor. The proposed method is divided into three steps. The first step is based on feature extraction from the input images using SIFT (Scale Invariant Feature Transform) descriptor. Each of the features is represented using one or more feature descriptors. In medical systems images used as patterns are also represented by feature vectors. In the second step eigen values and eigen vectors are extracted from each image. We apply PCA algorithm after we reduce the number of features by SIFT algorithm. The goal is to extract the important information as a set of new orthogonal variables called principal components. In the final step a nearest neighbor classifier is designed for classifying the images based on the extracted features. The algorithm is experimented in MATLAB and tested with the Caltech 101 database and the experimental results are shown.