Research on image complexity evaluation method based on color information

Assessment model for perceived visual complexity of painting images

This paper proposes a method of inserting a digital pattern having patient identity information in the medical retinal image without changing the perceptual property and without causing any loss of medical information of this image. To achieve this insertion of the digital signature identity of the patient is done in the singular value based decomposition (SVD) domain of the image. After the insertion of this digital signature is done in the retinal image a detailed comparative study and analysis is done between original image and marked image to test if all the medical information and features of the image is retained. The important feature of the medical image like blood arteries, macula and optic disc has been segmented from the original and stego-image. The experimental results indicate that the original and the stego image have similar perceptual properties and no medical information is lost in the process of digital watermarking. Features of the original and stego image has been analyzed and experimental results indicates that the variation in the features is minimal and do not affect the medical information which has been validated by professional ophthalmologists. The correlation of the features extracted is above 0.99 indicating the insertion of the digital pattern did not cause any loss of medical information in the image.

Visibility can be interpreted as the largest distance of an object that can be recognized or detected under a bright environment that can be used as an environmental indicator for weather conditions and air pollution. The accuracy of the classical approach of visibility calculation, in which meteorological laws and image feature extraction from digital images are used, depends on the quality and noise disturbances of the image. Therefore, artificial intelligence (AI) and digital image approaches have been proposed for visibility estimation in the past. Image features for the whole digital image are generated by pre-trained convolutional neural networks, and the Artificial Neural Network (ANN) is designed for correlation between image features and visibilities. Instead of using the information of the whole digital images, past research has been proposed to identify effective subregions from which image features are generated. A generalized regression neural network (GRNN) was designed to correlate the image features with the visibilities. Past research results showed that this method is more accurate than the classical approach of using handcrafted features. However, the selection of effective subregions of digital images is not fully automated and is based on manual selection by expert judgments. In this paper, we proposed an automatic effective subregion selection method using landmark object extraction techniques. Image features are generated from these LMO subregions, and the ANN is designed to approximate the mapping between LMO regions’ feature values and visibility values. The experimental results show that this approach can minimize the reductant information for ANN training and improve the accuracy of visibility estimation as compared to the single image approach.

Specific to the problem of feature description for colour image, a novel speeded-up robust features SURF descriptor of colour image-based quaternion CSURF-Q is proposed in this paper. Firstly, in order to represent the colour information of colour image effectively, the colour information among three channels is expressed by the three imaginary parts of quaternion. This can transform colour image to a pure quaternion matrix, which simplifies the representation process of image colour information. Secondly, the SURF features among three channels of colour image are extracted by using quaternion matrix. Because of the rotation invariance of quaternion norm, feature description vectors are generated as the form of quaternion norm. Finally, comparing CSURF-Q with SURF, FAIR-SURF, CSIFT, SIFT-CCH, colour-SURF and CHSIFT, the experiments prove that, when image appears affine changes, the correct matching of feature point pairs and time complexity are superior.

253 Background: To determine whether CT imaging features can provide quantitative biomarkers to differentiate HCC with pathologic B-catenin gene mutation and those without mutation. Methods: Quantitative imaging features were extracted from a database of manually labeled liver with enhancing and non-enhancing tumor tissue,which were established using multiphasic CT images from 17 patients. CT studies were done before each patient underwent surgical removal of the HCC, which were subjected to pathologic analysis to evaluate B-catenin mutation.The mean period between the CT studies and the pathologic analyses was 18 days. According to the pathology results, the patients were divided into two groups: HCC with CTNNB1 mutation and HCC without. Image feature extraction included image gradients, co-occurrence matrix, and pixel neighborhood statistics of the first, second, and third moments. Pairwise analyses of the imaging features were performed on the mutated and non-mutated HCC images and the background liver tissue of both groups. Independent samples t-test and Mann Whitney U test were performed to quantitatively compare between the means of the imaging features extracted from the tumor tissues of both groups and those extracted from the background liver tissue of both groups. Results: Imaging feature analysis of the pairwise difference between the mutated and non-mutated HCC scans for multiple pixel-neighborhood image features are statistically significant.The top stratifying image features include the skewness (p = 0.02), energy (p = .03), and entropy (p = .03) during the venous and arterial phase. Conclusions: This preliminary study demonstrates the feasibility of quantitative imaging feature extraction from CE-CT imaging to differentiate between HCC with proven B-catenin gene mutation and those without mutation. Non-invasive methods of identifying HCC with B-catenin mutations may be clinically beneficial since B-catenin is an important potential target in novel cancer therapies, and identifying B-catenin mutations may also help provide information regarding prognosis.Verifying the quantitative features in larger patient populations is needed to confirm the results of this study.

Background and Objectives: Brain Tumor Fusion-based Segments and Classification-Non-enhancing tumor (BTFSC-Net) is a hybrid system for classifying brain tumors that combine medical image fusion, segmentation, feature extraction, and classification procedures. Materials and Methods: to reduce noise from medical images, the hybrid probabilistic wiener filter (HPWF) is first applied as a preprocessing step. Then, to combine robust edge analysis (REA) properties in magnetic resonance imaging (MRI) and computed tomography (CT) medical images, a fusion network based on deep learning convolutional neural networks (DLCNN) is developed. Here, the brain images’ slopes and borders are detected using REA. To separate the sick region from the color image, adaptive fuzzy c-means integrated k-means (HFCMIK) clustering is then implemented. To extract hybrid features from the fused image, low-level features based on the redundant discrete wavelet transform (RDWT), empirical color features, and texture characteristics based on the gray-level cooccurrence matrix (GLCM) are also used. Finally, to distinguish between benign and malignant tumors, a deep learning probabilistic neural network (DLPNN) is deployed. Results: according to the findings, the suggested BTFSC-Net model performed better than more traditional preprocessing, fusion, segmentation, and classification techniques. Additionally, 99.21% segmentation accuracy and 99.46% classification accuracy were reached using the proposed BTFSC-Net model. Conclusions: earlier approaches have not performed as well as our presented method for image fusion, segmentation, feature extraction, classification operations, and brain tumor classification. These results illustrate that the designed approach performed more effectively in terms of enhanced quantitative evaluation with better accuracy as well as visual performance.

A large number of digital painting image resources cannot be directly converted into electronic form due to their differences in painting techniques and poor preservation of paintings. Moreover, the difficulty of extracting classification features can also lead to the consumption of human time and misclassification problems. The aim of this research is to address the challenges of converting various digital painting image resources into electronic form and the difficulties of accurately extracting classification features. The goal is to improve the usefulness and accuracy of painting image classification. Converting various digital painting image resources directly into electronic format and accurately extracting classification features are challenging due to differences in painting techniques and painting preservation, as well as the complexity of accurately extracting classification features. Overcoming these adjustments and improving the classification of painting features with the help of artificial intelligence (AI) techniques is crucial. The existing classification methods have good applications in different fields. But their research on painting classification is relatively limited. In order to better manage the painting system, advanced intelligent algorithms need to be introduced for corresponding work, such as feature recognition, image classification, etc. Through these studies, unlabeled classification of massive painting images can be carried out, while guiding future research directions. This study proposes an image classification model based on AI stroke features, which utilizes edge detection and grayscale image feature extraction to extract stroke features; and the convolutional neural network (CNN) and support vector machine are introduced into image classification, and an improved LeNet-5 CNN is proposed to achieve comprehensive assurance of image feature extraction. Considering the diversity of painting image features, the study combines color features with stroke features, and uses weighted K-means clustering algorithm to extract sample features. The experiment illustrates that the K-CNN hybrid model proposed in the study achieved an accuracy of 94.37% in extracting image information, which is higher than 78.24, 85.69, and 86.78% of C4.5, K-Nearest Neighbor (KNN), and Bi directional Long short-term Memory (BiLSTM) algorithms. In terms of image classification information recognition, the algorithms with better performance from good to poor are: the mixed model > BiLSTM > KNN > C4.5 model, with corresponding accuracy values of 0.938, 0.897, 0.872, and 0.851, respectively. And the number of fluctuation nodes in the mixed model is relatively small. And the sample search time is significantly shorter than other comparison algorithms, with a maximum recognition accuracy of 92.64% for the style, content, color, texture, and direction features of the image, which can effectively recognize the contrast and discrimination of the image. This method effectively provides a new technical means and research direction for digitizing image information.

With increasing number of vehicles in developing countries, the traditional practice of manual monitoring of vehicles is becoming cumbersome, ineffective and economically unviable. This study uses an image-processing-based frequency-domain approach using wavelet multiresolution analysis (MRA) to overcome the difficulties associated with the conventional approach of employing manual observation for vehicle identification. The classification algorithm uses features extracted from an image of vehicle license plate (VLP). Wavelet MRA technique is used to extract the features of image exploiting its abrupt change of intensities. As the features of an image are wavelet dependent, a number of wavelets have been used to extract features of the same image of a VLP. The wavelet that results in features for distinct classification is selected for this application. The case studies pertaining to vehicles in India validate the efficacy of the proposed methodology.

The paper proposes a novel method for estimating the optical flows from the sequentially captured images with using their own color information. The gradient method is well known as one of the conventional methods to estimate the flows, and then the spatial and temporal derivative of the images are used in the method. Since the color images have richer information than the monochrome ones, they should contribute for estimating the more precise optical flows. In our approach, the color derivative vector (CDV) is introduced to bring out the information in the color images for the optical flow estimation. The CDV is derived from the derivatives of color images, and the optimal CDV provides the concrete weighting values of the RGB data. The optimal CDV is obtained with using the eigenvalues and the eigenvectors of the matrix consisting of the spatial and temporal color derivatives.

Forensic watermarking is used in large-scale video-distribution applications to track digital pirates after they illegally leak videos. Existing methods either have a high embedding complexity or have troubles providing imperceptibility and robustness. Therefore, this paper proposes a novel watermarking method that has a low embedding complexity, as well as sufficient imperceptibility and robustness. The main novelty is that frames are replaced out of the loop, which has a very low complexity. This is inspired by A/B watermarking, yet applied on frame level rather than video-segment level. The resulting drift-error artifacts are used for robust watermark detection. Additionally, a faster watermark detection method is proposed at the cost of a decrease in embedding capacity. We show that the drift errors caused by frame replacement are imperceptible, and that our method has a negligible impact on the video bitrate. Moreover, we demonstrate a high level of robustness. These interesting properties come at the cost of a non-blind detection with a relatively high complexity, that is partially solved by the proposed fast detection method. Additionally, a high detection complexity is not necessarily a problem since detection occurs infrequently and recent speed-up solutions exist. In conclusion, the proposed method is a novel and scalable solution that enables secure large-scale video distribution.

As an important branch of artificial intelligence, computer vision plays a huge role in the rapid development of artificial intelligence. From a biological point of view, in the acquisition and processing of information, vision is much more important than hearing, touch, etc., because 70% of the human cerebral cortex is processing visual information. Therefore, advances in computer vision technology are critical to the development of artificial intelligence that is designed to allow machines to think and handle things like humans. The acquisition and processing of visual information has always been the focus of computer vision research, and it is also difficult. The main problem of traditional computer vision technology in the processing of visual information is that the extracted image features are less discriminative, the generalization ability of image features in complex background scenes is insufficient, and the recognition ability on object recognition is poor. In response to these problems, based on the visual neural mechanism, this paper establishes an appropriate computer model for the neuronal cells in the human primary visual cortex, models the recognition response mechanism of the visual ventral system, and performs image feature extraction on the training samples. And object recognition. The results show that compared with the traditional methods, the proposed method effectively improves the discrimination of image features, and the image features extracted under complex background scenes have good generalization ability. On this basis, the training samples can be effectively recognized. The results show that the model based on the visual neural mechanism, the recognition of the edge, orientation and contour of the training sample show the advantages of the biological vision mechanism in object recognition.

In this paper, the proposal system can achieve the more safety of RFID System with the 2-step authentication procedures for the enhancement about the security of general RFID systems. After authentication RFID Tag, additionally, the proposal system extract the characteristic information in the user image for acquisition of the additional authentication information of the user with the camera. In this paper, the system which was proposed more enforce the security of the automatic entrance and exit authentication system with the cognitive characters of RFID Tag and the extracted characteristic information of the user image through the camera. The RFID system which use the active tag and reader with 2.4GHz bandwidth can recognize the tag of RFID in the various output manner. Additionally, when the RFID system have errors, the characteristic information of the user image is designed to replace the RFID system as it compare with the similarity of the color, outline and input image information which was recorded to the database previously. In the result of experiment, the system can acquire more exact results as compared with the single authentication system when it using RFID Tag and the information of color characteristics.

In social networks, users can easily share information and express their opinions. Given the huge amount of data posted by many users, it is difficult to search for relevant information. In addition to individual posts, it would be useful if we can recommend groups of people with similar interests. Past studies on user preference learning focused on single-modal features such as review contents or demographic information of users. However, such information is usually not easy to obtain in most social media without explicit user feedback. In this paper, we propose a multimodal feature fusion approach to implicit user preference prediction which combines text and image features from user posts for recommending similar users in social media. First, we use the convolutional neural network (CNN) and TextCNN models to extract image and text features, respectively. Then, these features are combined using early and late fusion methods as a representation of user preferences. Lastly, a list of users with the most similar preferences are recommended. The experimental results on real-world Instagram data show that the best performance can be achieved when we apply late fusion of individual classification results for images and texts, with the best average top-k accuracy of 0.491. This validates the effectiveness of utilizing deep learning methods for fusing multimodal features to represent social user preferences. Further investigation is needed to verify the performance in different types of social media.

During the process of fine segmentation of medical images, although a single threshold can improve the efficiency of processing, there will be the problem of fuzzy features and non-convergence of threshold in denoising of details such as contour extraction. To extract contour information of medical images, a method based on multi-threshold optimization is proposed. This paper analyzes the influence of contour wave transformation on gray correlation degree and noise intensity of different medical images and improves the Bayesian threshold. The middle threshold function was improved by correlation characteristics of contour wave coefficients, and contour features of medical images were constrained by multiple thresholds. Based on the above, the dimension of the medical image was reduced by the wavelet multi-resolution analysis method, and the corresponding threshold search space was obtained. A genetic algorithm was used to find the best quasi threshold in the search space. Through this value, the attribute histogram of the medical image was established, the best feature extraction threshold of the medical image was obtained by the golden section method, and contour feature information of the medical image was extracted. The experimental results show that the proposed method can achieve the fast extraction of the contour feature information of running image, get an ideal feature extraction effect, and has high efficiency of feature extraction.

In this paper, we present an improved active shape model (ASM) for facial feature extraction. The original ASM method developed by Cootes et al. highly relies on the initialization and the representation of the local structure of the facial features in the image. We use color information to improve the ASM approach for facial feature extraction. The color information is used to localize the centers of the mouth and the eyes to assist the initialization step. Moreover, we model the local structure of the feature points in the RGB color space. Besides, we use 2D affine transformation to align facial features that are perturbed by head pose variations. In fact, the 2D affine transformation compensates for the effects of both head pose variations and the projection of 3D data to 2D. Experiments on a face database of 50 subjects show that our approach outperforms the standard ASM and is successful in facial feature extraction