Inspired by Weber's Law, this paper proposes a simple, yet very powerful and robust local descriptor, called the Weber Local Descriptor (WLD). It is based on the fact that human perception of a pattern depends not only on the change of a stimulus (such as sound, lighting) but also on the original intensity of the stimulus. Specifically, WLD consists of two components: differential excitation and orientation. The differential excitation component is a function of the ratio between two terms: One is the relative intensity differences of a current pixel against its neighbors, the other is the intensity of the current pixel. The orientation component is the gradient orientation of the current pixel. For a given image, we use the two components to construct a concatenated WLD histogram. Experimental results on the Brodatz and KTH-TIPS2-a texture databases show that WLD impressively outperforms the other widely used descriptors (e.g., Gabor and SIFT). In addition, experimental results on human face detection also show a promising performance comparable to the best known results on the MIT+CMU frontal face test set, the AR face data set, and the CMU profile test set.

/pdf/wld-a-robust-local-image-descriptor-1cbl4w5nom.pdf

WLD: A Robust Local Image Descriptor

Texture features for image classification and retrieval.

From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of highly discriminative intermediate features that we call Part-based One-vs.-One Features (POOFs). Each of these features specializes in discrimination between two particular classes based on the appearance at a particular part. We demonstrate the particular usefulness of these features for fine-grained visual categorization with new state-of-the-art results on bird species identification using the Caltech UCSD Birds (CUB) dataset and parity with the best existing results in face verification on the Labeled Faces in the Wild (LFW) dataset. Finally, we demonstrate the particular advantage of POOFs when training data is scarce.

/pdf/poof-part-based-one-vs-one-features-for-fine-grained-1y3g8nsnu6.pdf

POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation

The purpose of this paper is to present the most important achievements in the field of distribution power line inspection by mobile robots. Stimulated by the need for fast, accurate, safe and low-cost power line inspection, which would increase the quality of power delivery, the field of automated power line inspection has witnessed rapid development over the last decade. This paper addresses automated helicopter inspection, inspection with flying robots and inspection with climbing robots. The first attempts to automate power line inspection were conducted in the field of helicopter inspection. In recent years, however, the research was mostly focused on flying and climbing robots. These two types of robots for automated power line inspection are critically assessed according to four important characteristics: design requirements, inspection quality, autonomy and universality of inspection. Besides, some general not yet identified problems and tasks of inspection robots, which should be addressed in the future, are presented. In conclusion, the two robot types have specific benefits and drawbacks so that none can currently be considered generally advantageous.

A Survey of Mobile Robots for Distribution Power Line Inspection

advances in kernel methods support vector learning is available in our digital library an online access to it is set as public so you can get it instantly. Our books collection hosts in multiple countries, allowing you to get the most less latency time to download any of our books like this one. Merely said, the advances in kernel methods support vector learning is universally compatible with any devices to read.

Advances In Kernel Methods Support Vector Learning

A Single Tooth Segmentation Using PCA-Stacked Gabor Filter and Active Contour

Most of the existing methods focus mainly on the extraction of shape-based, rotation-based, and motion-based features, usually neglecting the relationship between hands and body parts, which can provide significant information to address the problem of similar sign words based on the backhand approach. Therefore, this paper proposes four feature-based models. The spatial–temporal body parts and hand relationship patterns are the main feature. The second model consists of the spatial–temporal finger joint angle patterns. The third model consists of the spatial–temporal 3D hand motion trajectory patterns. The fourth model consists of the spatial–temporal double-hand relationship patterns. Then, a two-layer bidirectional long short-term memory method is used to deal with time-independent data as a classifier. The performance of the method was evaluated and compared with the existing works using 26 ASL letters, with an accuracy and F1-score of 97.34% and 97.36%, respectively. The method was further evaluated using 40 double-hand ASL words and achieved an accuracy and F1-score of 98.52% and 98.54%, respectively. The results demonstrated that the proposed method outperformed the existing works under consideration. However, in the analysis of 72 new ASL words, including single- and double-hand words from 10 participants, the accuracy and F1-score were approximately 96.99% and 97.00%, respectively.

/pdf/backhand-approach-based-american-sign-language-words-1tub6jmq.pdf

Backhand-Approach-Based American Sign Language Words Recognition Using Spatial-Temporal Body Parts and Hand Relationship Patterns

Video shot boundary detection is the process of automatically detecting the meaningful boundary in video data. It becomes an essential pre-processing step to video analysis, summarisation and other content-based retrieval. Video frame feature representation also plays an important role in the process where it directly affects to the performance of the system. Histogram dissimilarity-based with the pre-processed features scheme are proposed to represent the temporal characteristic in videos. Motivated by the practical applications with moderate computational time, supervised abrupt shot boundary detection with averaged two-dependence estimators probabilistic classification learning scheme is proposed in this paper. The performance evaluation is performed by TRECVID 2007 videos dataset containing various types of video category. The performance of the proposed scheme can be expressed in terms of precision and recall to detect the correct abrupt video shot.

Abrupt shot boundary detection based on averaged two-dependence estimators learning

After COVID-19 pandemic, with the tremendously increasing reliance on digital media platform all over the world, advanced video surveillance, video content analysis, and video retrieval tasks have become an essential field which makes traditional method for shot boundary detection (SBD) less efficient, especially for gradual transition type shot boundary. SBD is an important preliminary step in video processing which helps to separate video sequences into shots. Large videos (news, national ceremony, sports, movies, etc.) contain several types of shot transitions (gradual, cut), and to detect them with higher accuracy an efficient SBD method is needed. Previous researchers have proposed methods for SBD by using Supervised machine learning approaches, however, data training is a limitation for them. Some previous papers have proposed unsupervised approaches, however detection for gradual transition shot boundaries has not achieved good accuracy. This paper proposes a distance calculating algorithms for SBD by using principal component analysis (PCA) features and then deep learning method to improve the detection precision of gradual transition shot boundary frames and normal frames. Firstly, PCA is used for feature extraction of the video frames and the most significant Eigenvectors and Eigenvalues are analyzed. Secondly, a distance calculating algorithm is used on the adjacent video frames depending on their Eigenvectors and Eigenvalues to determine the shot boundaries. Finally, to improve detection accuracy, false detection boundaries are reviewed and classified using CNN. Experimental results show the efficiency of the proposed method.

Video Shot Boundary Detection Using Principal Component Analysis (PCA) and Deep Learning

Air bubble impurity is one of critical defects on ribbed smoked sheets (RSSs). Only RSSs with few or without air bubbles are allowed in top industries such as wheel-manufacturing. However, air bubbles are difficult to detect because of their size, intensity and low contrast with the background. This paper proposes to apply the fractal dimension as a feature for RSS classification with regard to air bubble impurity. Images of RSS are captured in a controlled environment using a fluorescent light source. These images are resized and divided into 16 smaller areas. Then, the fractal dimension values of these areas are calculated. Finally, the standard deviation of the 16 fractal dimensions is computed for comparing with a predetermined threshold for classification. The experimentations with 500 images of RSSs of which half contains some air bubbles were conducted to verify the proposed method. The experimental results showed the classification accuracy of 98.00 % using the expert grading as reference.

Kosin Chamnongthai

Papers

A Single Tooth Segmentation Using PCA-Stacked Gabor Filter and Active Contour

Backhand-Approach-Based American Sign Language Words Recognition Using Spatial-Temporal Body Parts and Hand Relationship Patterns

Abrupt shot boundary detection based on averaged two-dependence estimators learning

Video Shot Boundary Detection Using Principal Component Analysis (PCA) and Deep Learning

Air bubbles detecting on ribbed smoked sheets based on fractal dimension