Field programmable gate array based target detection and gesture recognition

The move from Standard Definition (SD) to High Definition (HD) represents a six times increases in data, which needs to be processed. With expanding resolutions and evolving compression, there is a need for high performance with flexible architectures to allow for quick upgrade ability. The technology advances in image display resolutions, advanced compression techniques, and video intelligence. Software implementation of these systems can attain accuracy with tradeoffs among processing performance (to achieve specified frame rates, working on large image data sets), power and cost constraints. There is a need for new architectures to be in pace with the fast innovations in video and imaging. It contains dedicated hardware implementation of the pixel and frame rate processes on Field Programmable Gate Array (FPGA) to achieve the real-time performance. ^ The following outlines the contributions of the dissertation. (1) We develop a target detection system by applying a novel running average mean threshold (RAMT) approach to globalize the threshold required for background subtraction. This approach adapts the threshold automatically to different environments (indoor and outdoor) and different targets (humans and vehicles). For low power consumption and better performance, we design the complete system on FPGA. (2) We introduce a safe distance factor and develop an algorithm for occlusion occurrence detection during target tracking. A novel mean-threshold is calculated by motion-position analysis. (3) A new strategy for gesture recognition is developed using Combinational Neural Networks (CNN) based on a tree structure. Analysis of the method is done on American Sign Language (ASL) gestures. We introduce novel point of interests approach to reduce the feature vector size and gradient threshold approach for accurate classification. (4) We design a gesture recognition system using a hardware/ software co-simulation neural network for high speed and low memory storage requirements provided by the FPGA. We develop an innovative maximum distant algorithm which uses only 0.39% of the image as the feature vector to train and test the system design. Database set gestures involved in different applications may vary. Therefore, it is highly essential to keep the feature vector as low as possible while maintaining the same accuracy and performance^

The application of PCA as a movement pattern recognition technique: A proof of principle

Quantitative methods can help us understand how underlying attributes contribute to movement patterns. Applying principal components analysis (PCA) to whole-body motion data may provide an objective data-driven method to identify unique and statistically important movement patterns. Therefore, the primary purpose of this study was to determine if athletes’ movement patterns can be differentiated based on skill level or sport played using PCA. Motion capture data from 542 athletes performing three sport-screening movements (i.e. bird-dog, drop jump, T-balance) were analyzed. A PCA-based pattern recognition technique was used to analyze the data. Prior to analyzing the effects of skill level or sport on movement patterns, methodological considerations related to motion analysis reference coordinate system were assessed. All analyses were addressed as case-studies. For the first case study, referencing motion data to a global (lab-based) coordinate system compared to a local (segment-based) coordinate system affected the ability to interpret important movement features. Furthermore, for the second case study, where the interpretability of PCs was assessed when data were referenced to a stationary versus a moving segment-based coordinate system, PCs were more interpretable when data were referenced to a stationary coordinate system for both the bird-dog and T-balance task. As a result of the findings from case study 1 and 2, only stationary segment-based coordinate systems were used in cases 3 and 4. During the bird-dog task, elite athletes had significantly lower scores compared to recreational athletes for principal component (PC) 1. For the T-balance movement, elite athletes had significantly lower scores compared to recreational athletes for PC 2. In both analyses the lower scores in elite athletes represented a greater range of motion. Finally, case study 4 reported differences in athletes’ movement patterns who competed in different sports, and significant differences in technique were detected during the bird-dog task. Through these case studies, this thesis highlights the feasibility of applying PCA as a movement pattern recognition technique in athletes. Future research can build on this proof-of-principle work to develop robust quantitative methods to help us better understand how underlying attributes (e.g. height, sex, ability, injury history, training type) contribute to performance.

Face recognition using a unified 3D morphable model

We address the problem of 3D-assisted 2D face recognition in scenarios when the input image is subject to degradations or exhibits intra-personal variations not captured by the 3D model. The proposed solution involves a novel approach to learn a subspace spanned by perturbations caused by the missing modes of variation and image degradations, using 3D face data reconstructed from 2D images rather than 3D capture. This is accomplished by modelling the difference in the texture map of the 3D aligned input and reference images. A training set of these texture maps then defines a perturbation space which can be represented using PCA bases. Assuming that the image perturbation subspace is orthogonal to the 3D face model space, then these additive components can be recovered from an unseen input image, resulting in an improved fit of the 3D face model. The linearity of the model leads to efficient fitting. Experiments show that our method achieves very competitive face recognition performance on Multi-PIE and AR databases. We also present baseline face recognition results on a new data set exhibiting combined pose and illumination variations as well as occlusion.

Datasets, features, learning, and models in visual recognition

Visual recognition is a fundamental research topic in computer vision. This dissertation explores datasets, features, learning, and models used for visual recognition. In order to train visual models and evaluate different recognition algorithms, this dissertation develops an approach to collect object image datasets on web pages using an analysis of text around the image and of image appearance. This method exploits established online knowledge resources (Wikipedia pages for text; Flickr and Caltech data sets for images). The resources provide rich text and object appearance information. This dissertation describes results on two datasets. The first is Berg’s collection of 10 animal categories; on this dataset, we significantly outperform previous approaches. On an additional set of 5 categories, experimental results show the effectiveness of the method. Images are represented as features for visual recognition. This dissertation introduces a text-based image feature and demonstrates that it consistently improves performance on hard object classification problems. The feature is built using an auxiliary dataset of images annotated with tags, downloaded from the Internet. Image tags are noisy. The method obtains the text features of an unannotated image from the tags of its k-nearest neighbors in this auxiliary collection. A visual classifier presented with an object viewed under novel circumstances (say, a new viewing direction) must rely on its visual examples. This text feature may not change, because the auxiliary dataset likely contains a similar picture. While the tags associated with images are noisy, they are more stable when appearance changes. The performance of this feature is tested using PASCAL VOC 2006 and 2007 datasets. This feature performs well; it consistently improves the performance of visual object classifiers, and is particularly effective when the training dataset is small. With more and more collected training data, computational cost becomes a bottleneck, especially when training sophisticated classifiers such as kernelized SVM. This dissertation proposes a fast training algorithm called Stochastic Intersection Kernel Machine (SIKMA). This proposed training method will be useful for many vision problems, as it can produce a kernel classifier that is more accurate than a linear classifier, and can be trained on tens of thousands of examples in two minutes. It processes training examples one by one in a sequence, so memory cost is no longer the bottleneck to process large scale datasets. This dissertation applies this approach to train classifiers of Flickr groups with many group training examples. The resulting Flickr group prediction scores can be used to measure image similarity between two images. Experimental results on the Corel dataset and a PASCAL VOC dataset show the learned Flickr features perform better on image matching, retrieval, and classification than conventional visual features. Visual models are usually trained to best separate positive and negative training examples. However, when recognizing a large number of object categories, there may not be enough training examples for most objects, due to the intrinsic long-tailed distribution of objects in the real world. This dissertation proposes an approach to use comparative object similarity. The key insight is that, given a set of object categories which are similar and a set of categories which are dissimilar, a good object model should respond more strongly to examples from similar categories than to examples from dissimilar categories. This dissertation develops a regularized kernel machine algorithm to use this category dependent similarity regularization. Experiments on hundreds of categories show that our method can make significant improvement for categories with few or even no positive examples.

Engraulis encrasicolus (Linnaeus, 1758): technical report about extraction and recognition of the digestive tract contents in early stages of the life cycle

The study of ichthyio-plankton stages and its relations with the environment and other organisms is therefore crucial for a correct use of fishery resources. In this context, the extraction and the analysis of the content of the digestive tract, is a key method for the identification of the diet in early larval stages, the determination of the resources they rely on and possibly a comparison with the diet of other species. Additionally this approach could be useful in determination on occurrence of species competition. This technique is preceded by the analysis of morphometric data (Blackith & Reyment, 1971; Marcus, 1990), that is the acquisition of quantitative variables measured from the morphology of the object of study. They are linear distances, count, angles and ratios. The subsequent application of multivariate statistical methods, aims to quantify the changes in morphological measures between and within groups, relating them to the type and size of prey and evaluate if some changes appear in food choices along the larvae growth.

Age estimation in common sole Solea solea larvae: validation of daily increments and evaluation of a pattern recognition technique

Close similarities have been found between the otoliths of sea-caught and laboratory-reared larvae of the common sole Solea solea (L.), given appropriate temperatures and nourishment of the latter. But from hatching to mouth formation. and during metamorphosis, sole otoliths have proven difficult to read because the increments may be less regular and low contrast. In this study, the growth increments in otoliths of larvae reared at 12 degrees C were counted by light microscopy to test the hypothesis of daily deposition, with some results verified using scanning electron microscopy (SEM), and by image analysis in order to compare the reliability of the 2 methods in age estimation. Age was first estimated (in days posthatch) from light micrographs of whole mounted otoliths. Counts were initiated from the increment formed at the time of month opening (Day 4). The average incremental deposition rate was consistent with the daily hypothesis. However, the light-micrograph readings tended to underestimate the mean ages of the larvae. Errors were probably associated with the low-contrast increments: those deposited after the mouth formation during the transition to first feeding, and those deposited from the onset of eye migration (about 20 d posthatch) during metamorphosis. SEM failed to resolve these low-contrast areas accurately because of poor etching. A method using image analysis was applied to a subsample of micrograph-counted otoliths. The image analysis was supported by an algorithm of pattern recognition (Growth Demodulation Algorithm, GDA). On each otolith, the GDA method integrated the growth pattern of these larval otoliths to averaged data from different radial profiles, in order to demodulate the exponential trend of the signal before spectral analysis (Fast Fourier Transformation, FFT). This second method both allowed more precise designation of increments, particularly for low-contrast areas, and more accurate readings but increased error in mean age estimation. The variability is probably due to a still rough perception of otolith increments by the GDA method, counting being achieved through a theoretical exponential pattern and mean estimates being given by FFT. Although this error variability was greater than expected, the method provides for improvement in both speed and accuracy in otolith readings.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Football Video Annotation Based on Player Motion Recognition Using Enhanced Entropy

This paper presents a semi-parametric Algorithm for parsing football video structures. The approach works on a two interleaved based process that closely collaborate towards a common goal. The core part of the proposed method focus perform a fast automatic football video annotation by looking at the enhance entropy variance within a series of shot frames. The entropy is extracted on the Hue parameter from the HSV color system, not as a global feature but in spatial domain to identify regions within a shot that will characterize a certain activity within the shot period. The second part of the algorithm works towards the identification of dominant color regions that could represent players and playfield for further activity recognition. Experimental Results shows that the proposed football video segmentation algorithm performs with high accuracy.

Object detection and recognition in complex scenes

Dissertação de Mestrado, Engenharia Informática, Faculdade de Ciências e Tecnologia, Universidade do Algarve, 2014

Development of a new wine tasting method based on emotional responses

Mestrado Vinifera Euromaster - Instituto Superior de Agronomia - UL

Origin discrimination and quality evaluation of Gastrodiae rhizoma (Orchidaceae) by high-performance liquid chromatographic fingerprint

Purpose: To develop a high-performance liquid chromatography (HPLC) fingerprint method for the quality control and origin discrimination of Gastrodiae rhizoma . Methods: Twelve batches of G. rhizoma collected from Sichuan, Guizhou and Shanxi provinces in china were used to establish the fingerprint. The chromatographic peak (gastrodin) was taken as the reference peak, and all sample separation was performed on a Agilent C18 (250 mm×4.6 mmx5 μm) column with a column temperature of 25 °C. The mobile phase was acetonitrile/0.8 % phosphate water solution (in a gradient elution mode) and the flow rate of 1 mL/min. The detection wavelength was 270 nm. The method was validated as per the guidelines of Chinese Pharmacopoeia. Results: The chromatograms of the samples showed 11 common peaks, of which no. 4 was identified as that of Gastrodin. Data for the samples were analyzed statistically using similarity analysis and hierarchical cluster analysis (HCA). The similarity index between reference chromatogram and samples’ chromatograms were all > 0.80. The similarity index of G. rhizoma from Guizhou, Shanxi and Sichuan is evident as follows: 0.854 - 0.885, 0.915 - 0.930 and 0.820 - 0.848, respectively. The samples could be divided into three clusters at a rescaled distance of 7.5: S1 - S4 as cluster 1; S5 - S8 cluster 2, and others grouped into cluster 3. Conclusion: The findings indicate that HPLC fingerprinting technology is appropriate for quality control and origin discrimination of G. rhizoma.

Comparison of Computer-Based and Optical Face Recognition Paradigms

The main objectives of this thesis are to validate an improved principal components analysis (IPCA) algorithm on images; designing and simulating a digital model for image compression, face recognition and image detection by using a principal components analysis (PCA) algorithm and the IPCA algorithm; designing and simulating an optical model for face recognition and object detection by using the joint transform correlator (JTC); establishing detection and recognition thresholds for each model; comparing between the performance of the PCA algorithm and the performance of the IPCA algorithm in compression, recognition and, detection; and comparing between the performance of the digital model and the performance of the optical model in recognition and detection. The MATLAB © software was used for simulating the models. PCA is a technique used for identifying patterns in data and representing the data in order to highlight any similarities or differences. The identification of patterns in data of high dimensions (more than three dimensions) is too difficult because the graphical representation of data is impossible. Therefore, PCA is a powerful method for analyzing data. IPCA is another statistical tool for identifying patterns in data. It uses information theory for improving PCA. The joint transform correlator (JTC) is an optical correlator used for synthesizing a frequency plane filter for coherent optical systems. The IPCA algorithm, in general, behaves better than the PCA algorithm in the most of the applications. It is better than the PCA algorithm in image compression because it obtains higher compression, more accurate reconstruction, and faster processing speed with acceptable errors; in addition, it is better than the PCA algorithm in real-time image detection due to the fact that it achieves the smallest error rate as well as remarkable speed. On the other hand, the PCA algorithm performs better than the IPCA algorithm in face recognition because it offers an acceptable error rate, easy calculation, and a reasonable speed. Finally, in detection and recognition, the performance of the digital model is better than the performance of the optical model.

Pattern recognition methods for EMG prosthetic control

In this work we focus on pattern recognition methods related to EMG upper-limb prosthetic control. After giving a detailed review of the most widely used classification methods, we propose a new classification approach. It comes as a result of comparison in the Fourier analysis between able-bodied and trans-radial amputee subjects. We thus suggest a different classification method which considers each surface electrodes contribute separately, together with five time domain features, obtaining an average classification accuracy equals to 75% on a sample of trans-radial amputees. We propose an automatic feature selection procedure as a minimization problem in order to improve the method and its robustness.

Call recognition and individual identification of fish vocalizations based on automatic speech recognition: An example with the Lusitanian toadfish

The study of acoustic communication in animals often requires not only the recognition of species specific acoustic signals but also the identification of individual subjects, all in a complex acoustic background. Moreover, when very long recordings are to be analyzed, automatic recognition and identification processes are invaluable tools to extract the relevant biological information. A pattern recognition methodology based on hidden Markov models is presented inspired by successful results obtained in the most widely known and complex acoustical communication signal: human speech. This methodology was applied here for the first time to the detection and recognition of fish acoustic signals, specifically in a stream of round-the-clock recordings of Lusitanian toadfish (Halobatrachus didactylus) in their natural estuarine habitat. The results show that this methodology is able not only to detect the mating sounds (boatwhistles) but also to identify individual male toadfish, reaching an identification rate of ca. 95%. Moreover this method also proved to be a powerful tool to assess signal durations in large data sets. However, the system failed in recognizing other sound types.

A Highly Improved Method For Sensitive Determination Of Amitriptyline In Pharmaceutical Formulations Using An Unmodified Carbon Nanotube Electrode In The Presence Of Sulfuric Acid.

The present paper describes a novel, simple and reliable differential pulse voltammetric method for determining amitriptyline (AMT) in pharmaceutical formulations. It has been described for many authors that this antidepressant is electrochemically inactive at carbon electrodes. However, the procedure proposed herein consisted in electrochemically oxidizing AMT at an unmodified carbon nanotube paste electrode in the presence of 0.1 mol L(-1) sulfuric acid used as electrolyte. At such concentration, the acid facilitated the AMT electroxidation through one-electron transfer at 1.33 V vs. Ag/AgCl, as observed by the augmentation of peak current. Concerning optimized conditions (modulation time 5 ms, scan rate 90 mV s(-1), and pulse amplitude 120 mV) a linear calibration curve was constructed in the range of 0.0-30.0 μmol L(-1), with a correlation coefficient of 0.9991 and a limit of detection of 1.61 μmol L(-1). The procedure was successfully validated for intra- and inter-day precision and accuracy. Moreover, its feasibility was assessed through analysis of commercial pharmaceutical formulations and it has been compared to the UV-vis spectrophotometric method used as standard analytical technique recommended by the Brazilian Pharmacopoeia.