The massive volume of images produced in recent years has made image retrieval one of the topics of research in the field of machine vision and image processing. The main challenge of content-based image retrieval systems is to extract the appropriate feature vector for image description to enable image retrieval effectively. In this research, a content-based image retrieval framework is introduced. The introduced feature vector is a combination of low-level features and mid-level features of the image. Extraction of low-level features of the image, including color, shape and texture, was performed using multi-level autocorrelation, discrete wavelet transform and fractal dimension analysis. Mid-level features are also extracted using the deep Boltzmann machine and by learning the low-level features of the image. The resulting feature vector is adjusted with 1K Corel database images and the performance of the proposed framework is also measured on 5K and 10K Corel databases. The best evaluation results are reported on 99.5%, 99.2% and 99.6% of the mentioned databases, respectively.

In this paper we describe a novel noise-robust texture classification method using joint multiscale local binary pattern. The first step in texture classification is to describe the texture by extracting different features. So far, several methods have been developed for this topic, one of the most popular ones is Local Binary Pattern (LBP) method and its variants such as Completed Local Binary Pattern, Extended Local Binary Pattern, Local Temporary Pattern, Local Contrast Pattern, etc. In order to extract the features of a texture in different scales, the LBP method can be implemented in a multi-scale framework. For this purpose, the extracted feature vectors at different scales are usually concatenated together to produce the final feature vector with a longer length. But such a scheme has two main shortcomings. First, the LBP method is very sensitive to noise, hence by adding noise to a texture image, its feature vectors may change significantly. Second, by increasing the number of the scales, the length of the final feature vector is increased accordingly. This action increases the classification process time, and it may reduce the classification accuracy. To mitigate these shortcomings, this paper presents a method based on multiscale LBP, which has a better resistance against white Gaussian noise, while the length of its final feature vector is equal to the length of the final feature vector produced by the original LBP method. To implement the proposed method, we used 17 circular binary masks that contain 8 directed first-order masks, 8 directed second-order masks and 1 undirected mask. These masks have positive and negative weightes and each group of these masks have different radius which after convolution with input image extract features in different scales. Experiments were performed on four test groups of Outex database. Experimental results show that the proposed method is superior to the existing state-of-the-art methods. The complexity of proposed method is also analyzed. The results show that in this method, despite obtaining excellent classification accuracy, the complexity of the method has not changed much and even its complexity is less than some of the existing state-of-the-art methods.

Representing 3D models in diverse fields have automatically paved the way of storing, indexing, classifying, and retrieving 3D objects. Classification and retrieval of 3D models demand that the 3D models represent in a way to capture the local and global shape specifications of the object. This requires establishing a 3D descriptor or signature that summarizes the pivotal shape properties of the object. Therefore, in this work, a new shape descriptor has been proposed to recognize 3D model utilizing global characteristics. To perform feature extraction in the proposed method, the bounding meshed sphere surrounding the 3D model and concentrated from the outside toward the center of the model. Then, the length of the path which the sphere's vertices travel from the beginning to the model’s surface will be measured. These values are exploited to compute the path function. The engendered function is robust against isometric variations and it is appropriate for recognizing non-rigid models. In the following, the Fourier transform of the path function is calculated as the features vector, and then the extracted features vector is utilized in SVM classifier. By exploiting the properties of the magnitude response of the Fourier transform of the real signals, the model can be analyzed in the lower space without losing the inherent characteristics, and no more pose normalization is needed. The simulation results based on the SVM classifier on the McGill data set show the proposed method has the highest accuracy (i.e. 79.7%) among the compared related methods. Moreover, the confusion matrix for performing 70% trained SVM classifier indicates the suitable distinguishing ability for similar models and does not have a high computational complexity of model processing in 3D space.

In this paper a heuristic method, called Moving Window K-Nearest Neighbors (MW-KNN), for detecting QRS complexes was developed. To achieve this, a new simple 2-D geometrical feature space (feature space dimension was equal to 2) was extracted from the original electrocardiogram (ECG) signal. In this method, a sliding window was moved sample-by-sample on the preprocessed ECG signal. During each forward sliding, an artificial image was generated from the excerpted segment allocated in the window. Each image estimated by a 300×300 pixels matrix. Then, a pictorial-geometrical feature extraction technique based on curve-length was applied to each image for establishment of an appropriate feature space. Afterwards the K-Nearest Neighbors (KNN) Classification method was designed and implemented to the ECG signal. The proposed methods were applied to DAY general hospital high resolution holter data. For detection of QRS complex the average values of sensitivity Se = 99.93% and positive predictivity P+ = 99.88% were obtained.