Local gradient patterns (LGP): An effective local-statistical-feature extraction scheme for no-reference image quality assessment

Approximate back-projection method for improving lateral resolution in circular-scanning-based photoacoustic tomography

PURPOSE

In circular-scanning-based photoacoustic tomography (PAT), the effect of finite transducer aperture has not been effectively resolved. The goal of this paper is to propose a practical reconstruction method that accounts for the finite transducer aperture to improve the lateral resolution.

METHODS

We for the first time propose to calculate the spatial-temporal response (STR) of the employed finite-sized transducer in a forward model, and then compensate the time delay and the directional sensitivity of the transducer in the framework of the back-projection method. Both simulation and phantom experiments were carried out to evaluate the lateral resolution improvement with the proposed method. The performance of this new method for imaging complicated targets was also assessed by calculating the mean image gradient.

RESULTS

Simulation results showed that with this new method the lateral resolution for off-center targets can be as good as that for the center targets. Phantom experimental results showed that this new method can improve the lateral resolution more than two times for a point target about 5 mm far from the rotation center. Phantom experimental results also showed that many blurred fine structures of a piece of leaf veins at the off-center regions were well restored with the new method, and the mean image gradient improved about 1.3 times.

CONCLUSION

The proposed new method can effectively account for the effect of finite transducer aperture for circular-scanning-based PAT in homogenous acoustic media. This new method also features its robustness and computational efficiency, so that it is a worthy replacement to the conventional back-projection algorithm in circular-scanning-based PAT. This new method can be of great importance to the design of circular-scanning or spherical-scanning-based PAT systems.

Digital image processing technology under backpropagation neural network and K-Means Clustering algorithm on nitrogen utilization rate of Chinese cabbages

The purposes are to monitor the nitrogen utilization efficiency of crops and intelligently evaluate the absorption of nutrients by crops during the production process. The research object is Chinese cabbage. The Chinese cabbage population with different agricultural parameters is constructed through different densities and nitrogen fertilizer application rates based on digital image processing technology, and an estimation NC (Nitrogen Content) model is established. The population is classified through the K-Means Clustering algorithm using the feature extraction method, and the Chinese cabbage population quality BPNN (Backpropagation Neural Network) model is constructed. The nonlinear mapping relationship between different agricultural parameters and population quality, and the contribution rate of each indicator, are studied. The nitrogen utilization of Chinese cabbage is monitored effectively. Results demonstrate that the proposed NC estimation model has correlation coefficients above 0.70 in different growth stages. This model can accurately estimate the NC of the Chinese cabbage population. The results of the Chinese cabbage population quality BPNN model show that the population planting density based on the seedling number is reasonable. The constructed population quality evaluation model has a high R2 value and a comparatively low RMSE (Root Mean Square Error) value for the quality evaluation of Chinese cabbage in different periods, showing that it applies to evaluate the population quality of Chinese cabbage in different growth stages. The constructed nitrogen utilization model and quality evaluation model can monitor the nutrient utilization of crops in different growth stages, ascertain the agricultural characteristics of other yield groups in different growth stages, and clarify the performance of agricultural parameters in different growth stages. The above results can provide some ideas for crop growth intelligent detection.

Healthcare Professional in the Loop (HPIL): Classification of Standard and Oral Cancer-Causing Anomalous Regions of Oral Cavity Using Textural Analysis Technique in Autofluorescence Imaging

Oral mucosal lesions (OML) and oral potentially malignant disorders (OPMDs) have been identified as having the potential to transform into oral squamous cell carcinoma (OSCC). This research focuses on the human-in-the-loop-system named Healthcare Professionals in the Loop (HPIL) to support diagnosis through an advanced machine learning procedure. HPIL is a novel system approach based on the textural pattern of OML and OPMDs (anomalous regions) to differentiate them from standard regions of the oral cavity by using autofluorescence imaging. An innovative method based on pre-processing, e.g., the Deriche-Canny edge detector and circular Hough transform (CHT); a post-processing textural analysis approach using the gray-level co-occurrence matrix (GLCM); and a feature selection algorithm (linear discriminant analysis (LDA)), followed by k-nearest neighbor (KNN) to classify OPMDs and the standard region, is proposed in this paper. The accuracy, sensitivity, and specificity in differentiating between standard and anomalous regions of the oral cavity are 83%, 85%, and 84%, respectively. The performance evaluation was plotted through the receiver operating characteristics of periodontist diagnosis with the HPIL system and without the system. This method of classifying OML and OPMD areas may help the dental specialist to identify anomalous regions for performing their biopsies more efficiently to predict the histological diagnosis of epithelial dysplasia.

GFNB: Gini index-based Fuzzy Naive Bayes and blast cell segmentation for leukemia detection using multi-cell blood smear images

The blood cell counting and classification ensures the evaluation and diagnosis of a number of diseases. The analysis of white blood cells (WBCs) permits us to detect the acute lymphoblastic leukemia (ALL), a type of blood cancer that causes fatality when untreated. At present, the morphological analysis of blood cells is performed manually by skilled operators, which holds numerous drawbacks. The manual techniques for leukemia detection are time-consuming and show less accurate results. Hence, there is a need for an automatic method for detecting leukemia. In order to overcome the demerits associated with the manual methods of counting and classifying, an automatic method of blast cell counting and leukemia classification is progressed. This paper proposes a leukemia detection method, using the Gini index-based Fuzzy Naive Bayes (GFNB) classifier that is the integration of Gini index and Fuzzy Naive Bayes classifier. Initially, the input multi-cell blood smear image is subjected to pre-processing, and the blast cell is segmented using the adaptive thresholding. Then, the blast cells are counted using the proposed classifier so as to decide the presence of leukemia for the effective diagnosis. Experimental analysis using the ALL-IDB1 database confirms that the proposed method operates better than the existing methods in terms of accuracy, specificity, and sensitivity that are found to be 0.9591, 0.9599, and 1, respectively. The experimental results reveal that the proposed method is reliable and accurate. Also, the proposed system can help the physicians to improve and speed up their process.Graphical abstract Leukemia is caused by the excess production of the immature leucocytes in the bone marrow that expose the human body to lose the tendency to fight against the diseases. Leukemia classification is highly needed as in the later stage, failure of the diagnosis steps may lead to the death of the person. Moreover, some countries do not have any study against the diagnosis steps of leukemia and it highly exists among the low-income people. In order to analyze the type of leukemia and to provide an effective diagnosis strategy, the paper presents a fast and highly accurate classification method. The main aim of the paper is to propose a method to perform the leukemia classification through the segmentation and classification of the WBC cells using the multi-cell blood smear images. The major steps involved in the leukemia classification are pre-processing, segmentation, feature extraction, and classification. The input blood smear image is enhanced in the pre-processing step and the pre-processed image is subjected to segmentation using the LUV color transformation and Adaptive Thresholding strategy. The features are extracted from the individual segments and they are presented to the classifier for the classification. The features extracted are shape, texture, and count of the blast cells, for which the grid-based shape extraction, local gradient pattern (LGP)-based texture features, and pixel threshold-based counting of the blast cells are employed. The proposed classifier is developed using the Gini index and Fuzzy Naive Bayes classifier.

Attention-based fusion network for human eye-fixation prediction in 3D images

Human eye-fixation prediction in 3D images is important for many 3D applications, such as fine-grained 3D video object segmentation and intelligent bulletproof curtains. While the vast majority of existing 2D-based approaches cannot be applied, the main challenge lies in the inconsistency, or even conflict, between the RGB and depth saliency maps. In this paper, we propose a three-stream architecture to accurately predict human visual attention on 3D images end-to-end. First, a two-stream feature extraction network based on advanced convolutional neural networks is trained for RGB and depth, and hierarchical information is extracted from each ResNet-18. Then, these multi-level features are fed into the channel attention mechanism to suppress the feature space inconsistency and make the network focus on a significant target. The enhanced saliency map is fused step-by-step by VGG-16 to generate the final coarse saliency map. Finally, each coarse map is refined empirically through refinement blocks, and the network's own identification errors are corrected based on the acquired knowledge, thus converting the prediction saliency map from coarse to fine. The results of comparison of our model with six other state-of-the-art approaches on the NUS dataset (CC of 0.5579, KLDiv of 1.0903, AUC of 0.8339, and NSS of 2.3373) and the NCTU dataset (CC of 0.8614, KLDiv of 0.2681, AUC of 0.9143, and NSS of 2.3795) indicate that the proposed model consistently outperforms them by a considerable margin as it fully employs the channel attention mechanism.

Local and Global Feature Learning for Blind Quality Evaluation of Screen Content and Natural Scene Images

The blind quality evaluation of screen content images (SCIs) and natural scene images (NSIs) has become an important, yet very challenging issue. In this paper, we present an effective blind quality evaluation technique for SCIs and NSIs based on a dictionary of learned local and global quality features. First, a local dictionary is constructed using local normalized image patches and conventional -means clustering. With this local dictionary, the learned local quality features can be obtained using a locality-constrained linear coding with max pooling. To extract the learned global quality features, the histogram representations of binary patterns are concatenated to form a global dictionary. The collaborative representation algorithm is used to efficiently code the learned global quality features of the distorted images using this dictionary. Finally, kernel-based support vector regression is used to integrate these features into an overall quality score. Extensive experiments involving the proposed evaluation technique demonstrate that in comparison with most relevant metrics, the proposed blind metric yields significantly higher consistency in line with subjective fidelity ratings.

No-reference stereoscopic image quality assessment guided by visual hierarchical structure and binocular effects

Stereoscopic image quality assessment (SIQA) is an essential technique for modern 3D image and video processing systems serving as performance evaluators and monitors. However, the study on SIQA remains immature due to the complexity of the human visual system (HVS) and binocular effects that binocular vision brings about. To overcome the difficulties, a novel method is proposed that extracts and quantifies image quality-aware features related to cortex areas in charge of visual quality perception, rather than attempting to rigorously simulate the biological processing in HVS, so that the predicting accuracy is preserved while the computational complexity remains moderate. Meanwhile, binocular effects including binocular rivalry and visual discomfort are taken into consideration. Moreover, the proposed method can be operated completely without the assistance of reference images, indicating its wide practical usages. Compared to state-of-the-art works, our method shows evident superiority in terms of effectiveness and robustness.