Fast Image Retrieval Using Classified Vector Quantization of Feature Space

In the field of computer vision and image processing CBIR (Content based image retrieval) system become an active research area. The CBIR technique involves feature extraction based on image features (like color, shape and texture) and defining rules for comparing image. A classifier is also used by authors for image classification. For this purpose an image database taken from James Z. Wang research group website is used by many authors. Due to enormous increase in the size of database traditional methods of image retrieval by using keywords does not provide accurate result. Thus the concept of CBIR system is emerged. In last couple of years many method of feature extraction is developed but since now researcher are not able to develop a system which has gained high accuracy of human visual perception in distinguishing pictures. Therefore earlier researchers have concentrated to increase the retrieval accuracy of CBIR system by using different combination of features. The objective of this paper is to present review on a CBIR technique which combined four kinds of features set including every kind of feature for developing feature vector. Color based features (histogram), statistical features (mean, median and standard deviation), spatial features (Gabor feature and wavelet features) and texture features (GLCM) is used for forming feature vector. A SVM classifier is used with CBIR system to increase retrieval accuracy. SVM (support vector machine) is a machine learning classifier which provides good classification accuracy. Keywords: CBIR, SVM, NN, GLCM, HSV Color space, Euclidean distance matrix.

This paper introduces a new CBIR system based on two different approaches in order to achieve the retrieval efficiency and accuracy. Color and texture information is extracted and used in this work to form the feature vector. To do the texture feature extraction this system uses DCT and DCT Wavelet transform to generate the feature vectors of the query and database images. Color information extraction process includes separation of image into R, G and B planes. Further each plane is divided into 4 blocks and for each block row mean vectors are calculated. DCT and DCT wavelet is applied over row mean vector of each block separately and 4 sets of DCT and DCT wavelet coefficients are obtained respectively. Out of these few coefficients are selected from each block and arranged in consecutive order to form the feature vector of the image. Variable size feature vectors are formed by changing the no of coefficients selected from each row vector. Total 18 different sets are obtained by changing the no of coefficients selected from each block. These two different feature databases obtained using DCT and DCT wavelet are then tested using 100 query images from 10 different categories. Euclidean distance is used as similarity measure to compare the image features. Euclidean distance calculated is sorted into ascending order and cluster of first 100 images is selected to count the images which are relevant to the query image. Results are further refined using second level thresholding which uses three criteria which can be applied to first level results. Results obtained are showing the better performance by DCT wavelet as compare to DCT transform. Keywords-component; DCT; DCT wavelet; Eucidean distance. I. INTRODUCTION Large amount of images are being generated, stored and used daily in various real life applications through various fields like engineering, medical sciences, biometrics, architectural designs and drawings and many other areas. Although various techniques are being designed and used to store the images efficiently, still it demands to search new effective and accurate techniques to retrieve these images easily from large volume of databases. Text based image retrieval techniques have tried in this direction which has got many constraints and drawbacks associated with it which is continuously encouraging the researchers to come up with the new techniques to retrieve the images based on contents instead of text annotations. Image contents are broadly classified into global and local contents. Local contents define the local attributes of the image like color, shape and texture

Content-based techniques enable retrieval of remotely sensed data based on low-level features. However, the deep gap between low-level features and high-level semantics concepts is a major obstacle to more effective image retrieval. Therefore, a semantics-based retrieval approach was implemented. The semantics classifiers are trained using heterogeneous features from a group of satellite images. The proposed approach is mainly composed of two steps. The first step is to form hierarchical semantics classifiers based on the low-level features of the training images. In the second step, unknown satellite images are classified into a certain semantics class if their feature vectors are located in the corresponding feature space. To achieve an effective and at the same time efficient identification of the multiple semantics classes within the satellite scenes, an approximation approach was developed. At the query time, the system retrieves the satellite images based on semantics classes extracted from the query image or provided directly by the users

With the evolution of the Internet, and the availability of image capturing devices such as advanced cameras, picture scanners, the size of advanced image accumulation is expanding quickly. Efficient image searching, browsing and retrieval devices are required by clients from different domains, including remote sensing, fashion, wrongdoing prevention, publishing, medicine, architecture, etc. Here we are extracting color mean features and color standard deviation feature with the proposed method consists of HMMD (Hue Min Max Difference) color plane. It is proved in research work that HMMD along with color mean features and color standard deviation feature is tend to reduced the size of feature vectors, storage space and gives high performance than, RGB-color mean feature. Further, HMMD color space model will be used to improve the feature extraction and improve the precision. At the end, results are presented to show the efficiency of the proposed method. Keywords: HMMD, CBIR, Feature Extraction, Precision, Recall.

Road visual navigation relies on accurate road models. This study was aimed at proposing an improved scale-invariant feature transform (SIFT) algorithm for recovering depth information from farmland road images, which would provide a reliable path for visual navigation. The mean image of pixel value in five channels (R, G, B, S and V) were treated as the inspected image and the feature points of the inspected image were extracted by the Canny algorithm, for achieving precise location of the feature points and ensuring the uniformity and density of the feature points. The mean value of the pixels in 5×5 neighborhood around the feature point at an interval of 45o in eight directions was then treated as the feature vector, and the differences of the feature vectors were calculated for preliminary matching of the left and right image feature points. In order to achieve the depth information of farmland road images, the energy method of feature points was used for eliminating the mismatched points. Experiments with a binocular stereo vision system were conducted and the results showed that the matching accuracy and time consuming for depth recovery when using the improved SIFT algorithm were 96.48% and 5.6 s, respectively, with the accuracy for depth recovery of –7.17%-2.97% in a certain sight distance. The mean uniformity, time consuming and matching accuracy for all the 60 images under various climates and road conditions were 50%-70%, 5.0-6.5 s, and higher than 88%, respectively, indicating that performance for achieving the feature points (e.g., uniformity, matching accuracy, and algorithm real-time) of the improved SIFT algorithm were superior to that of conventional SIFT algorithm. This study provides an important reference for navigation technology of agricultural equipment based on machine vision. Keywords: scale-invariant feature transform (sift), feature matching, canny operator, energy method of feature point, farmland road, depth recovery, visual navigation DOI: 10.25165/j.ijabe.20191204.4821 Citation: Yao L J, Hu D, Yang Z D, Li H B, Qian M B. Depth recovery for unstructured farmland road image using an improved SIFT algorithm. Int J Agric & Biol Eng, 2019; 12(4): 141–147.

International audience

The medical image can be divided into two major classes that are anatomical image and functional image. Magnetic resonance image (MRI) and computed tomography (CT) belong to the anatomical image, which can show an outline of an organ and a tissue clearly. The functional image can show the image of the organ and the tissue metabolism situation. Positron emission tomography (PET) and single photon emission computed tomography (SPECT) are also part of the functional image. In this paper, we use 4-[18F]-ADAM to measure serotonin transporter changes and find the relation with major depressive disorder in CT / PET three-dimensional image. In clinical diagnosis, based on the video imaging methods can be divided into the anatomy and function of these two categories. Therefore, the combination of anatomical and functional imaging can provide more useful information. In the study, we use CT image to get the reference position, and combine with isotope metabolic situation from PET. We use the integrated image to do 3D image and count serotonin transporter with different points in time, and measure the variance about serotonin transporter changes in the organization of the metabolism and distribution. We use the variance to find the relation and compare the score using Hamilton Depression Rating Scale by experienced psychiatrists. After the test case, measuring the size distribution of serotonin transporter to depression patients can do a preliminary classification.

One of the techniques in region based image retrieval (RBIR) is comparing the global feature of an entire image and the local feature of image’s sub-block in query and database image. The determined sub-block must be able to detect an object with varying sizes and locations. So the sub-block with flexible size and location is needed. We propose a new method for local feature extraction by determining the flexible size and location of sub-block based on the transition region in region based image retrieval. Global features of both query and database image are extracted using invariant moment. Local features in database and query image are extracted using hue, saturation, and value (HSV) histogram and local binary patterns (LBP). There are several steps to extract the local feature of sub-block in the query image. First, preprocessing is conducted to get the transition region, then the flexible sub-block is determined based on the transition region. Afterward, the local feature of sub-block is extracted. The result of this application is the retrieved images ordered by the most similar to the query image. The local feature extraction with the proposed method is effective for image retrieval with precision and recall value are 57%.

Recently, digital content has become a significant and inevitable asset of or any enterprise and the need for visual content management is on the rise as well. Content-based image retrieval has attracted voluminous research in the last decade paving way for development of numerous techniques and systems besides creating interest on fields that support these systems. CBIR indexes the images based on the features obtained from visual content so as to facilitate speedy retrieval. In this thesis work, we present a steerable pyramid based image retrieval system that uses color, contours and texture as visual features to describe the content of an image region. We have initially used steerable pyramid to extract texture features from query image and database images and store them in feature vectors. Second, to speed up retrieval and similarity computation, the database images are classified and the extracted regions are clustered according to their feature vectors using median vector algorithm. This process is performed before query matching takes place. Therefore to answer a query our system does not need to search the entire database images; instead just a number of candidate images are required to be searched for image similarity. Our proposed system has the advantage of increasing the retrieval accuracy and decreasing the retrieval time. The experimental evaluation of the system is based on a satellite and medical image database. From the experimental results, it is evident that our system performs significantly better and faster compared with other existing systems. In our analysis, we provide a comparison between retrieval results based on features extracted from the whole image using steerable pyramid with median vector and features extracted from same image without median vector. The results demonstrate that each type of feature is effective for a particular type of images according to its semantic contents, and using a combination of them giving better retrieval results for almost all different classes of images in the dataset. Â

This paper presents a new trademark image retrieval method based on the region orientation information entropy. In the first stage, image is rotated according to principal orientation, and the object region in the rotated image is extracted. Then, the object region is partitioned into a lot of sub-blocks. In the third stage, the information entropy of each partitioned region is computed, which construct a feature vector for describing the shape of the image. Finally, the Euclidean distance is adopted to measure the similarity between the images based on the feature vector of each image obtained. Experiments performed on a database containing more than 2,000 trademark images show that the region orientation information entropy keeps good invariance under rotation, translation, scale and the retrieved results satisfy human visual perception very well.

We consider the solution of elliptic partial differential equations with random input data. In particular, we are interested in the mean and the correlation of the solution of these partial differential equations. Once the correlation is available, the variance can be computed from its diagonal. If the dependence of the solution on the random input data is linear and the mean of the input data is available, the mean of the solution can be computed whenever the corresponding partial differential equation can be solved. When the correlation of the input data is available, the correlation of the solution is given as the solution of a higher dimensional partial differential equation in the product domain. A Galerkin discretization yields a matrix equation with a typically densely populated right-hand side. This and the higher dimension of the problem makes the equation prohibitively expensive to solve. Since existing approaches to these correlation equations are known to struggle for roughly correlated input data, we use hierarchical matrices and their corresponding arithmetic to represent and solve the matrix equation. The regularity assumptions required for hierarchical matrices can be justified on sufficiently smooth domains. The feasibility of the approach is illustrated for finite element and boundary element discretizations and several specialities of hierarchical matrices for finite element discretizations are discussed. An almost linear scaling with respect to the dimension of the used finite element spaces is verified. The nonlinear dependence of the solution on the random input data is exemplarily discussed for the case of random domains. Extending previous perturbation approaches, we can linearize the problem and can compute the mean and the correlation up to third order accuracy in almost linear time. We discuss that these spaces can become even fourth order accurate under certain circumstances. A full convergence analysis is presented, which shows that higher order boundary elements are required for the solution of the problem. Therefore, we develop a fast multipole method for higher order boundary element methods on parametric surfaces.

Deep point-to-subspace metric learning for sketch-based 3D shape retrieval

Segmentation is a low-level processing aimed at the partition of an image in disjoint regions, each one homogeneous with respect to some properties like intensity, texture, shape, etc. Such a task is needed in many high-level processing and applications in such diverse fields as remote-sensing, medical imaging, video coding, and industrial automation, just to name a few. In this work of thesis, we first deal with the problem of color based image segmentation, that is based on some form of homogeneity in the color/spectral properties of the image, and then move to the more complex task of texture based segmentation, where the aim is to recognize complex structures in the image which are typically non homogeneous in terms of spectral properties. Concerning color based segmentation, we focus on a specific class of Markov Random Field (MRF) probability models, namely the Tree-Structured Markov Random Fields (TS-MRF), recently proposed to provide a hierarchical multiscale description of images. Based on such a model, the unsupervised image segmentation is carried out by means of a sequence of nested class splits, where each class is modeled as a local binary MRF. As a first contribution, we first extend the model to generic tree structures removing the unnecessary binary constraint, and then devise a new TS-MRF unsupervised segmentation technique which improves upon the original algorithm by selecting a better tree structure and eliminating spurious classes. Such results are obtained by using the Mean-Shift procedure to estimate the number of pdf modes at each node, and to obtain a more reliable initial clustering for subsequent MRF optimization. To this end, we devise a new reliable and fast clustering algorithm based on the Mean-Shift technique, which makes use of a variable-bandwidth strategy based on the k-Nearest Neighbors (k-NN) technique, and is implemented with a speed-up strategy that cuts significantly the computational complexity. Experimental results on synthetic data and real life images from the remote sensing domain prove the potential of the proposed method. Turning to texture based segmentation, we present a novel multiscale texture model, and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled in turn by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The ``fragmentation'' step allows one to find the elementary textures of the model, while the ``reconstruction'' step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural images from the Berkeley dataset. Finally, an application of the TFR algorithm for the unsupervised segmentation of multiresolution remotely sensed images is proposed, based on the significant presence of textural content in last generation high-resolution satellite images. The obtained results further assess the potential of the proposed method for such real life applications.

Image searching is most interesting in the field of the computer vision. Every day many digital images are coming into the web. User is attracted to automatic image retrieval from this large dataset. Many methods which are introduced in this last ten years for image retrieval based on the similarity, size of database, image classification, similar group of images finding, performance of retrieval. when the size of database is increasing image similarity finding It is big task for the researchers to give the efficient solutions. Content-Based Image Retrieval (CBIR) systems are used in order to retrieve image from image dataset. In our proposed method, we are utilizing clustering method for retrieve the images. Each Image converted into gray form and calculated the threshold values for 10000 images for each image extracted cluster mean values using k-mean method and stored into the database. In first method query image mean values are comparing using mean distances between query image and database images. In second method group of images are selecting from the image database with similar features and finding the distance difference of the each image and considered the squires of the all distances and make a sum and divide with the number of cluster values then make in sequential order of the images. Main aim of this work is to extract images with good similarity when the images that are retrieved based on query image. Above mention methods are given good performance.

Objective To evaluate the image quality and registration accuracy of a three-dimensional (3D) dynamic phantom in four-dimensional computed tomography (4DCT) and four-dimensional cone-beam computed tomography (4DCBCT). Methods The Computerized Imaging Reference Systems Dynamic Thorax Phantom Model 008A was scanned to get 4DCT and 4DCBCT images. Two balls with different diameters (O= 1 cm and O= 2 cm) were used to simulate tumors with different sizes. The motion mode of the balls was 3D sinusoidal motion at 0.25 Hz (the amplitudes along the x, y, and z axes were ±1.0 cm, ±0.4 cm, and ±0.2 cm, respectively). Gross target volumes (GTVs) from 10-phase bins, internal gross target volumes (IGTV), and target volumes on maximum intensity projection (MIP) and mean intensity projection (MeanIP) images were contoured and calculated. Target volumes on 4DCT or 4DCBCT images were compared with the static and dynamic volumes of the balls (VS and VD). The matching index (MI) of target volumes between the 4DCT and 4DCBCT images was analyzed after rigid image registration. Results The GTV in each phase of the image was larger than VS. The difference between the average GTV derived from 10 phases of 4DCT or 4DCBCT images and Vs of the small ball was larger than that of the large ball (35.03% vs. 22.66%; 32.62% vs. 17.00%). All the IGTVs and target volumes on MIP images were slightly larger than VD, but target volumes on MeanIP images were smaller than VD. The average MI of 10-phase bins of the small ball was smaller than that of the large ball (66.76% vs. 82.21%). Moreover, MIs of IGTV, MIP, and MeanIP of the small ball were also smaller than those of the large ball (77.39% vs. 90.29%; 75.90% vs. 89.28%; 74.47% vs. 82.74%). Conclusions In the case of a relatively small tumor volume and a relatively large motion amplitude, 4DCT and 4DCBCT should be used with caution for comparison of image registration. Key words: Tomography, X-ray computed; Tomography, X-ray computed, cone-beam; Imaging registration; Phantom