Biometric-based techniques have emerged as the most promising option for individual recognition. This task is still a challenge for computer vision systems. Several approaches to adult image recognition, which include the deep neural network and traditional classifier, have been proposed. Different image condition factors such as expressions, occlusion, poses, and illuminations affect the facial recognition system. A reasonable amount of illumination variations between the gallery and probe images need to be taken into account in adult image recognition algorithms. In the context of adult image verification, illumination variation plays a vital role and this factor will most likely result in misclassification. Different architectures and different parameters have been tested in order to improve the classification’ s accuracy. This proposed method contains four steps, which begin with Fuzzy Deep Neural Network Segmentation. This step is employed in order to segment an image based on illumination intensity. Histogram Truncation and Stretching is utilized in the second step for improving histogram distribution in the segmented area. The third step is Contrast Limited Adaptive Histogram Equalization (CLAHE). This step is used to enhance the contrast of the segmented area. Finally, DCT-II is applied and low-frequency coefficients are selected in a zigzag pattern for illumination normalization. In the proposed method, AlexNet architecture is used, which consists of 5 convolutional layers, max-pooling layers, and fully connected layers. The image is passed through a stack of convolutional layers after fuzzy neural representation, where we used filter 8 × 8. The convolutional stride is fixed to 1 pixel. After every convolution, there is a subsampling layer, which consists of a 2×2 kernel to do max pooling. This can help to reduce the training time and compute complexity of the network. The proposed scheme will be analyzed and its performance in accuracy and effectiveness will be evaluated. In this research, we have used 80, 400 images, which are imported from two datasets-the Compaq and Poesia datasets-and used images found on the Internet.

An effective approach for bone image anal­ysis, including segmentation and recognition is presented in this paper. Bone segmenta­tion is carried out by K-means clustering of the bone image, whereas the recognition phase is based on fea­ture extraction and two-level statistical classification. The proposed approach has applications in medicine and vet­erinary anatomy studies, orthopedics, paleontology and archaeology. Several image features, including geomet­ric and moment invariants (regular and Zernike), are de­rived for recognition. The first-level classification is used to distinguish different kinds of bone and the second-level to recognize the right animal to which the bone belongs. Two-dimensional structures, called cluster-property and cluster-features matrices, have been employed to evalu­ate different bone characteristics. Experimental results for the first-level recognition exhibit better performance of the geometric features compared to moment invariants and Zernike moments. On the other hand, Zernike moments showed supremacy in differential diagnosis at the second level to recognize animals. 

In recent years, automatic recognition of vehicle logos has become one of the important issues in modern cities. This is due to the unlimited increase of cars and transportation systems that make it impossible to be fully managed and monitored by human. In this research, an automatic real-time logo recognition system for moving cars is introduced based on histogram manipulation. In the proposed system, after locating the area that contains the logo, image matching technique and textural features are utilized separately for vehicle logo recognition. Experimental results show that these two methods are able to recognize four types of logo (Peugeot, Renault, Samand and Mazda) with an acceptable performance, 96% and 90% on average for image matching and textural features extraction methods, respectively.

Introduction: Facial emotion recognition plays an important role in social interactions. Impairment in this area causes a deficit in individuals’ social competency. The main objective of this study is to evaluate the accuracy and speed of facial emotion recognition at different levels of image blurring in healthy participants.Method: images of faces of all participants, displaying different emotions including happiness, sadness and anger along with neural expression in different levels of blurring, were viewed. They were instructed to detect the emotions accurately as soon as possible.Results: the results show that the accuracy of recognition of happiness was significantly higher than that for negative emotions such as anger and sadness. The neutral expression was recognized to be worse than happiness and better than negative emotions. Sadness was less quickly and more accurately than anger. The more the image blurred, the more the recognition of accuracy and speed was reduced.Conclusion: the accuracy and speed recognition of different emotions diminish due to the increased level of image blurring. Happiness, along with neutral expression, when displayed in blurred images, are always recognized with greater accuracy and speed than negative emotions (sadness and anger).

In recent years, facial expression recognition, as an interesting problem in computer vision has been performed by means of static and dynamic methods. Dynamic information plays an important role in recognizing facial expression in the image sequences. However, using the entire dynamic information in the expression image sequences is of higher computational cost compared to the static methods. To reduce the computational cost, instead of entire image sequence, only neutral and emotional faces can be employed. In the previous research, this idea was used by means of Difference of Local Binary Pattern Histogram Sequences (DLBPHS) method in which facial important small displacements were vanished by subtracting Local Binary Pattern (LBP) features of neutral and emotional face images. In this paper, a novel approach is proposed to utilize two face images. In the proposed method, the face component displacements are highlighted by subtracting neutral image from emotional image; then, LBP features are extracted from the difference image as well as the emotional one. Then, the feature vector is created by concatenating two LBP histograms. Finally, a Support Vector Machine (SVM) is used to classify the extracted feature vectors. The proposed method is evaluated on standard databases and the results show a significant accuracy improvement compared to DLBPHS.

recognition of hand writing on paper, on display or on air is an important challenge in computer vision. Air-writing recocognition is especially difficult due to three dimentionality of space. In this research work the aim is recognizing persian digits which are written in air in front of a Kineckt sensor using a fingertip and the sensor can detect the digit using its depth image. For hand and fingertip segmentation we use K-means algorithm. To extract the features we use a novel method called slope variation detection, and to classify the features Hidden Markov Models (HMM) is used. recognition rate of Persian digits using a local database with 10 times mutual validation is 96%. This novel method was compared with some other similar methods in the literature. The results confirm relative priority of the proposed method.

In the traditional methods of analyzing minerals in thin sections, the boundaries of the minerals were manually separated and each section was labeled. This approach is expensive and requires high expertise and experience. Therefore, an automatic identification system is essential in this field. Such a system can increase the accuracy and reduce human error, cost and time of mineral identification. The aim of this study is to propose an automated identification system which uses image processing to identify and classify existing minerals.The main steps of the proposed method include collecting images from thin sections, segmentation, feature extraction and classification. After creating the image database, the JSEG algorithm is applied for segmentation. Then, the color and texture features in both RGB and HSI color spaces are extracted from each region and are sent to the classifier for classification, which labels each segment as a mineral. In this study, the efficiency of six different classifiers has been evaluated. According to the results, the Bagged Tree classifier has the highest accuracy of 95.52% and the lowest Mean Absolute Error of 0.04. Also, all classifiers have accuracies of over 93%, which indicates that the proposed feature extraction method is able to properly identify minerals.