Image block feature vectors based on a singular-value information metric and color-texture description

Robust classification of pharmaceuticals in an industrial process is an important step for validation of the final product. Especially for pharmaceuticals with similar visual appearance a quality control is only possible if a reliable algorithm based on easily obtainable spectroscopic data is available. We used Principal Component Analysis (PCA) and Support Vector Machines (SVM) on Raman spectroscopy data from a compact Raman system to classify several look-alike pharmaceuticals. This paper describes the data gathering and analysis process to robustly discriminate 19 different pharmaceuticals with similar visual appearance. With the described process we successfully identified all given pharmaceuticals which had a significant amount of active ingredients. Thus automatic validation of these pharmaceuticals in a process can be used to prevent wrong administration of look-alike drugs in an industrial setting, e.g. patient individual blistering.

Performance analysis of colour descriptors for parquet sorting

Vehicle make and model classification is crucial to the operation of an intelligent transportation system (ITS). Fine-grained vehicle information such as make and model can help officers uncover cases of traffic violations when license plate information cannot be obtained. Various techniques have been developed to perform vehicle make and model classification. However, it is very hard to identify the make and model of vehicles with highly similar visual appearances. The classifier contains a lot of potential for mistakes because the vehicles look very similar but have different models and manufacturers. To solve this problem, a fine-grained classifier based on convolutional neural networks with a multi-task learning approach is proposed in this paper. The proposed method takes a vehicle image as input and extracts features using the VGG-16 architecture. The extracted features will then be sent to two different branches, with one branch being used to classify the vehicle model and the other to classify the vehicle make. The performance of the proposed method was evaluated using the InaV-Dash dataset, which contains an Indonesian vehicle model with a highly similar visual appearance. The experimental results show that the proposed method achieves 98.73% accuracy for vehicle make and 97.69% accuracy for vehicle model. Our study also demonstrates that the proposed method is able to improve the performance of the baseline method on highly similar vehicle classification problems.

Different features describe different views of visual appearance, multi-view based methods can integrate the information contained in each view and improve the image clustering performance. Most of the existing methods assume that the importance of one type of feature is the same to all the data. However, the visual appearance of images are different, so the description abilities of different features vary with different images. To solve this problem, we propose a group-aware multi-view fusion approach. Images are partitioned into groups which consist of several images sharing similar visual appearance. We assign different weights to evaluate the pairwise similarity between different groups. Then the clustering results and the fusion weights are learned by an iterative optimization procedure. Experimental results indicate that our approach achieves promising clustering performance compared with the existing methods.

We are developing a dietary assessment system that records daily food intake through the use of food images. Recognizing food in an image is difficult due to large visual variance with respect to eating or preparation conditions. This task becomes even more challenging when different foods have similar visual appearance. In this paper we propose to incorporate two types of contextual dietary information, food co-occurrence patterns and personalized learning models, in food image analysis to reduce ambiguity in food visual appearance and improve food recognition accuracy. We evaluate our model on 1453 food images acquired by 45 participants in natural eating conditions. The result shows that incorporating contextual dietary information improves the food categorization accuracy by about 10%.

In content based image retrieval (CBIR) process, every image has been represented in a compact set of local visual features i.e. color, texture, and/or shape of images. This set of local visual features is known as feature vector. In the CBIR process, feature vectors of images have been used to represent or to identify similar images in adequate way. As a result, feature vector construction has always been considered as an important issue since it must reflect proper image semantics using minimal amount of data. The proposed CBIR scheme is based on the combination of color and texture features. In this work initially, we have converted the given RGB image into HSV color image. Subsequently, we have considered H (hue), S (saturation), and V (intensity) components for extraction of visual image features. The texture features have been extracted from the V component of the image using 2D dual-tree complex wavelet transform (2D DT-CWT) where it analyzes the textural patterns in six different directions i.e. ±15\(^{\circ }\), ±45\(^{\circ }\), and ±75\(^{\circ }\). At the same time, we have computed the probability histograms of H and S components of the image respectively and subsequently those are divided into non-uniform bins based on cumulative probability for extraction of color based features. So, in this work both the color and texture features have been extracted simultaneously. Finally, the obtained features have been concatenated to attain the final feature vector and same is considered in image retrieval process. We have tested the novelty and performance of the proposed work in two Corel, two objects, and, a texture image datasets. The experimental results reveal the acceptable retrieval performances for different types of datasets.

This study represents an innovative automatic method for black and white films colorization using texture features and a multilayer perceptron artificial neural network. In the proposed method, efforts are made to remove human interference in the process of colorization and replace it with an artificial neural network (ANN) which is trained using the features of the reference frame. Later, this network is employed for automatic colorization of the remained black and white frames. The reference frames of the black and white film are manually colored. Using a Gabor filter bank, texture features of all the pixels of the reference frame are extracted and used as the input feature vector of the ANN, while the output will be the color vector of the corresponding pixel. Finally, the next frames’ feature vectors are fed respectively to the trained neural network, and color vectors of those frames are the output. Applying AVI videos and using various color spaces, a series of experiments are conducted to evaluate the proposed colorization process. This method needs considerable time to provide a reasonable output, given rapidly changing scenes. Fortunately however, due to the high correlation between consecutive frames in typical video footage, the overall performance is promising regarding both visual appearance and the calculated MSE error. Apart from the application, we also aim to show the importance of the low level features in a mainly high level process, and the mapping ability of a neural network.

In order to solve the problem of action recognition in short video and capture the key information of video, this paper first proposes a KGAF-means method for key frame extraction. The KGAF-means method is based on the clustering principle and combines the K-means algorithm with the artificial fish swarm algorithm to realize the key frame sequence extraction. Based on the extracted key frame sequence, the RGB image and the optical flow image are separately extracted by the improved dual-stream variable convolution network. Then, using the cascading method, the image feature vector and the optical flow feature vector are fused to obtain the fused feature vector for action recognition. The selected data set is the Charades data set. The experimental results show that the mAP value of the method is 22.9 on the public dataset Charades. And the results show that the proposed method has better robustness than other network models and improves the short video action recognition effect.

Development of a plastic waste treatment process by combining deep eutectic solvent (DES) pretreatment and bioaugmentation with a plastic-degrading bacterial consortium

Nowadays, surgical removal remains the standard method to treat brain tumors. During surgery, the neurosurgeon may encounter difficulties to delimitate tumor boundaries and the infiltrating areas as they have a similar visual appearance to adjacent healthy zones. These infiltrating residuals increase the tumor recurrence risk, which decreases the patient’s post-operation survival time. To help neurosurgeons improve the surgical act by accurately delimitating healthy from cancerous areas, our team is developing an intraoperative multimodal imaging tool. It consists of a two-photon fluorescence fibered endomicroscope that is intended to provide a fast, real-time, and reliable diagnosis information. In parallel to the instrumental development, a large optical database is currently under construction in order to characterize healthy and tumor brain tissues with their specific optical signature using multimodal analysis of the endogenous fluorescence. Our previous works show that this multimodal analysis could provide a reliable discrimination response between different tissue types based on several optical indicators. Here, our goal is to show that the two-photon fibered endomicroscope is able to provide, based on the same approved indicators in the tissue database, the same reliable response that could be used intraoperatively. We compared the spectrally resolved and time-resolved fluorescence signal, generated by our two-photon bimodal endoscope from 46 fresh brain tissue samples, with a similar signal provided by a standard reference benchtop multiphoton microscope that has been validated for tissue diagnosis. The higher excitation efficiency and collection ability of an endogenous fluorescence signal were shown for the endoscope setup. Similar molecular ratios and fluorescence lifetime distributions were extracted from the two compared setups. Spectral discrimination ability of the bimodal endoscope was validated. As a preliminary step before tackling multimodality, the ability of the developed bimodal fibered endoscope to excite and to collect efficiently as well as to provide a fast exploitable high-quality signal that is reliable to discriminate different types of human brain tissues was validated.

ObjectiveTo evaluate the hypothesis that anthropometric dimensions derived from a person’s manifold-regression predicted three-dimensional (3D) humanoid avatar are accurate when compared to their actual circumference, volume, and surface area measurements acquired with a ground-truth 3D optical imaging method. Avatars predicted using this approach, if accurate with respect to anthropometric dimensions, can serve multiple purposes including patient metabolic disease risk stratification in clinical settings.MethodsManifold regression 3D avatar prediction equations were developed on a sample of 570 adults who completed 3D optical scans, dual-energy X-ray absorptiometry (DXA), and bioimpedance analysis (BIA) evaluations. A new prospective sample of 84 adults had ground-truth measurements of 6 body circumferences, 7 volumes, and 7 surface areas with a 20-camera 3D reference scanner. 3D humanoid avatars were generated on these participants with manifold regression including age, weight, height, DXA %fat, and BIA impedances as potential predictor variables. Ground-truth and predicted avatar anthropometric dimensions were quantified with the same software.ResultsFollowing exploratory studies, one manifold prediction model was moved forward for presentation that included age, weight, height, and %fat as covariates. Predicted and ground-truth avatars had similar visual appearances; correlations between predicted and ground-truth anthropometric estimates were all high (R2s, 0.75–0.99; all p < 0.001) with non-significant mean differences except for arm circumferences (%D ~ 5%; p < 0.05). Concordance correlation coefficients ranged from 0.80–0.99 and small but significant bias (p < 0.05 – 0.01) was present with Bland-Altman plots in 13 of 20 total anthropometric measurements. The mean waist to hip circumference ratio predicted by manifold regression was non-significantly different from ground-truth scanner measurements.Conclusions3D avatars predicted from demographic, physical, and other accessible characteristics can produce body representations with accurate anthropometric dimensions without a 3D scanner. Combining manifold regression algorithms into established body composition methods such as DXA, BIA, and other accessible methods provides new research and clinical opportunities.

LaTeX is a very popular platform for writing papers in economics, mainly due to its superior aesthetics in print. The question is whether the aesthetic (and other) benefits of adopting LaTeX outweigh the opportunity costs of learning and using LaTeX, which can be high even for experienced users. FaKe LaTeX using Microsoft Word has a remarkably similar visual appearance to papers produced in native LaTeX and it is easy to learn and use. This low cost alternative may be appealing to many economists.

Optical signal intensity incorporated rice seed cultivar classification using optical coherence tomography

Use of natural emulsifiers in model coffee creamers: Physical properties of quillaja saponin-stabilized emulsions

Left ventricular thrombus attenuation characterization in cardiac computed tomography angiography