Hand gesture recognition using topological features

Multimedia Tools and Applications - Hand Gestures Recognition (HGR) is one of the main areas of research for Human Computer Interaction applications. Most existing approaches are based on local or...     

Fast approximate string matching

Approximate string matching is an important operation in information systems because an input string is often an inexact match to the strings already stored. Commonly known accurate methods are computationally expensive as they compare the input string to every entry in the stored dictionary. This paper describes a two-stage process. The first uses a very compact n-gram table to preselect sets of roughly similar strings. The second stage compares these with the input string using an accurate method to give an accurately matched set of strings. A new similarity measure based on the Levenshtein metric is defined for this comparison. The resulting method is both computationally fast and storage-efficient.     

Applications of approximate string matching to 2D shape recognition

A new method for the recognition of arbitrary two-dimensional (2D) shapes is described. It is based on string edit distance computation. The recognition method is invariant under translation, rotation, scaling and partial occlusion. A set of experiments are described demonstrating the robustness and reliability of the proposed approach.     

Tries for approximate string matching

Tries offer text searches with costs which are independent of the size of the document being searched, and so are important for large documents requiring spelling checkers, case insensitivity, and limited approximate regular secondary storage. Approximate searches, in which the search pattern differs from the document by k substitutions, transpositions, insertions or deletions, have hitherto been carried out only at costs linear in the size of the document. We present a trie based method whose cost is independent of document size. Our experiments show that this new method significantly outperforms the nearest competitor for k=0 and k=1, which are arguably the most important cases. The linear cost (in k) of the other methods begins to catch up, for our small files, only at k=2. For larger files, complexity arguments indicate that tries will outperform the linear methods for larger values of k. The indexes combine suffixes and so are compact in storage. When the text itself does not need to be stored, as in a spelling checker, we even obtain negative overhead: 50% compression. We discuss a variety of applications and extensions, including best match (for spelling checkers), case insensitivity, and limited approximate regular expression matching     

复杂背景下的手势识别

目的 手势识别是人机交互领域的热点问题。针对传统手势识别方法在复杂背景下识别率低,以及现有基于深度学习的手势识别方法检测时间长等问题,提出了一种基于改进TinyYOLOv3算法的手势识别方法。方法 对TinyYOLOv3主干网络重新进行设计,增加网络层数,从而确保网络提取到更丰富的语义信息。使用深度可分离卷积代替传统卷积,并对不同网络层的特征进行融合,在保证识别准确率的同时,减小网络模型的大小。采用CIoU（complete intersection over union）损失对原始的边界框坐标预测损失进行改进,将通道注意力模块融合到特征提取网络中,提高了定位精度和识别准确率。使用数据增强方法避免训练过拟合,并通过超参数优化和先验框聚类等方法加快网络收敛速度。结果 改进后的网络识别准确率达到99.1%,网络模型大小为27.6 MB,相比原网络（TinyYOLOv3）准确率提升了8.5%,网络模型降低了5.6 MB,相比于YOLO（you only look once）v3和SSD（single shot multibox detector）300算法,准确率略有降低,但网络模型分别减小到原来的1/8和1/3左右,相比于YOLO-lite和MobileNet-SSD等轻量级网络,准确率分别提升61.12%和3.11%。同时在自制的复杂背景下的手势数据集对改进后的网络模型进行验证,准确率达到97.3%,充分证明了本文算法的可行性。结论 本文提出的改进Tiny-YOLOv3手势识别方法,对于复杂背景下的手势具有较高的识别准确率,同时在检测速度和模型大小方面都优于其他算法,可以较好地满足在嵌入式设备中的使用要求。     

Layered architecture for real time sign recognition: Hand gesture and movement

Sign and gesture recognition offers a natural way for human–computer interaction. This paper presents a real time sign recognition architecture including both gesture and movement recognition. Among the different technologies available for sign recognition data gloves and accelerometers were chosen for the purposes of this research. Due to the real time nature of the problem, the proposed approach works in two different tiers, the segmentation tier and the classification tier. In the first stage the glove and accelerometer signals are processed for segmentation purposes, separating the different signs performed by the system user. In the second stage the values received from the segmentation tier are classified. In an effort to emphasize the real use of the architecture, this approach deals specially with problems like sensor noise and simplification of the training phase.     

Hand gesture recognition using Leap Motion via deterministic learning

With the development of multimedia technology, traditional interactive tools, such as mouse and keyboard, cannot satisfy users’ requirements. Touchless interaction has received considerable attention in recent years with benefit of removing barriers of physical contact. Leap Motion is an interactive device which can be used to collect information of dynamic hand gestures, including coordinate, acceleration and direction of fingers. The aim of this study is to develop a new method for hand gesture recognition using jointly calibrated Leap Motion via deterministic learning. Hand gesture features representing hand motion dynamics, including spatial position and direction of fingers, are derived from Leap Motion. Hand motion dynamics underlying motion patterns of different gestures which represent Arabic numbers (0-9) and capital English alphabets (A-Z) are modeled by constant radial basis function (RBF) neural networks. Then, a bank of estimators is constructed by the constant RBF networks. By comparing the set of estimators with a test gesture pattern, a set of recognition errors are generated. The average L₁ norms of the errors are taken as the recognition measure according to the smallest error principle. Finally, experiments are carried out to demonstrate the high recognition performance of the proposed method. By using the 2-fold, 10-fold and leave-one-person-out cross-validation styles, the correct recognition rates for the Arabic numbers are reported to be 94.2%, 95.1% and 90.2%, respectively, for the English alphabets are reported to be 89.2%, 92.9% and 86.4%, respectively.     

New algorithms for fixed-length approximate string matching and approximate circular string matching under the Hamming distance

This paper proposes new algorithms for fixed-length approximate string matching and approximate circular string matching under the Hamming distance. Fixed-length approximate string matching and approximate circular string matching are special cases of approximate string matching and have numerous direct applications in bioinformatics and text searching. Firstly, a counter-vector-mismatches (CVM) algorithm is proposed to solve fixed-length approximate string matching with k-mismatches. The development of CVM algorithm is based on the parallel summation of counters located in the same machine word. Secondly, a parallel counter-vector-mismatches (PCVM) algorithm is proposed to accelerate CVM algorithm in parallel. The PCVM algorithm is integrated into two-level parallelisms that exploit not only word-level parallelism but also data parallelism via parallel environments such as multi-core processors and graphics processing units (GPUs). In the particular case of adopting GPUs, a shared-mem parallel counter-vector-mismatches (PCVMsmem) scheme can be implemented from PCVM algorithm. The PCVMsmem scheme can exploit the memory model of GPUs to optimize performance of PCVM algorithm. Finally, this paper shows several methods to adopt CVM and PCVM algorithms in case the input pattern is in circular structure. In the experiments with real DNA packages, our proposed algorithms and scheme work greatly faster than previous bit-vector-mismatches and parallel bit-vector-mismatches algorithms.     

Cache-oblivious index for approximate string matching

This paper revisits the problem of indexing a text for approximate string matching. Specifically, given a text T of length n and a positive integer k, we want to construct an index of T such that for any input pattern P, we can find all its k-error matches in T efficiently. This problem is well-studied in the internal-memory setting. Here, we extend some of these recent results to external-memory solutions, which are also cache-oblivious. Our first index occupies O((nlog^kn)/B) disk pages and finds all k-error matches with O((|P|+occ)/B+log^knloglog_Bn) I/Os, where B denotes the number of words in a disk page. To the best of our knowledge, this index is the first external-memory data structure that does not require Ω(|P|+occ+poly(logn)) I/Os. The second index reduces the space to O((nlogn)/B) disk pages, and the I/O complexity is O((|P|+occ)/B+log^k(k+1)nloglogn).     

Hand gesture recognition using a neural network shape fitting technique

A new method for hand gesture recognition that is based on a hand gesture fitting procedure via a new Self-Growing and Self-Organized Neural Gas (SGONG) network is proposed. Initially, the region of the hand is detected by applying a color segmentation technique based on a skin color filtering procedure in the YCbCr color space. Then, the SGONG network is applied on the hand area so as to approach its shape. Based on the output grid of neurons produced by the neural network, palm morphologic characteristics are extracted. These characteristics, in accordance with powerful finger features, allow the identification of the raised fingers. Finally, the hand gesture recognition is accomplished through a likelihood-based classification technique. The proposed system has been extensively tested with success.     

Hand number gesture recognition using recognized hand parts in depth images

In this paper, we present a novel approach of recognizing hand number gestures using the recognized hand parts in a depth image. Our proposed approach is divided into two stages: (i) hand parts recognition by random forests (RFs) and (ii) rule-based hand number gestures recognition. In the first stage, we create a database (DB) of synthetic hand depth silhouettes and their corresponding hand parts-labeled maps and then train RFs with the DB. Via the trained RFs, we recognize or label the hand parts in a depth silhouette. In the second stage, based on the information of the recognized or labeled hand parts, hand number gestures are recognized according to our derived rules. In our experiments, we quantitatively and qualitatively evaluated our hand parts recognition system with synthetic and real data. Then, we tested our hand number gesture recognition system with real data. Our results show the average recognition rate of 97.80 % over the ten hand number gestures from five different subjects.     

Hand posture and gesture recognition technology

Hand gestures that are performed by one or two hands can be categorized according to their applications into different categories including conversational, controlling, manipulative and communicative gestures. Generally, hand gesture recognition aims to identify specific human gestures and use them to convey information. The process of hand gesture recognition composes mainly of four stages: hand gesture images collection, gesture image preprocessing using some techniques including edge detection, filtering and normalization, capture the main characteristics of the gesture images and the evaluation (or classification) stage where the image is classified to its corresponding gesture class. There are many methods that have been used in the classification stage of hand gesture recognition such as Artificial Neural Networks, template matching, Hidden Markov Models and Dynamic Time Warping. This exploratory survey aims to provide a progress report on hand posture and gesture recognition technology.     

Sublinear approximate string matching and biological applications

Given a text string of lengthn and a pattern string of lengthm over ab-letter alphabet, thek differences approximate string matching problem asks for all locations in the text where the pattern occurs with at mostk differences (substitutions, insertions, deletions). We treatk not as a constant but as a fraction ofm (not necessarily constant-fraction). Previous algorithms require at leastO(kn) time (or exponential space). We give an algorithm that is sublinear time0((n/m)k log _b m) when the text is random andk is bounded by the threshold m/(log_b m + O(1)). In particular, whenk=o(m/log_b m) the expected running time iso(n). In the worst case our algorithm is O(kn), but is still an improvement in that it is practical and uses0(m) space compared with0(n) or0(m ²). We define three problems motivated by molecular biology and describe efficient algorithms based on our techniques: (1) approximate substring matching, (2) approximate-overlap detection, and (3) approximate codon matching. Respectively, applications to biology are local similarity search, sequence assembly, and DNA-protein matching.This work was supported in part by NSF Grants CCR-87-04184 and FD-89-02813; by the Human Genome Center, Lawrence Berkeley Laboratory, supported by the Director, Office of Health and Environmental Research, of the U.S. Department of Energy under Contract DE-AC03-76SF00098; and by Department of Energy Grants DE-FG03-90ER60999 and DE-FG02-91ER61190. Earlier versions of this paper appeared as [8] and part of [5].     

Optimal spaced seeds for faster approximate string matching

Filtering is a standard technique for fast approximate string matching in practice. In filtering, a quick first step is used to rule out almost all positions of a text as possible starting positions for a pattern. Typically this step consists of finding the exact matches of small parts of the pattern. In the followup step, a slow method is used to verify or eliminate each remaining position. The running time of such a method depends largely on the quality of the filtering step, as measured by its false positives rate. The quality of such a method depends on the number of true matches that it misses, that is, on its false negative rate. A spaced seed is a recently introduced type of filter pattern that allows gaps (i.e. do not cares) in the small sub-pattern to be searched for. Spaced seeds promise to yield a much lower false positives rate, and thus have been extensively studied, though heretofore only heuristically or statistically. In this paper, we show how to design almost optimal spaced seeds that yield no false negatives.     

基于Bag of Features的手势识别

基于视觉的手势识别中,手势的识别效果易受手势旋转,光照亮度的影响,针对该问题,借鉴了目标识别和图像检索领域的Bag of Features(特征袋)算法,将Bag of Features算法应用到手势识别领域.通过SURF(加速鲁棒性特征)算法提取手势图像的特征描述符,使手势对尺度、旋转、光照具有很强的适应力,再应用Bag of Features算法把SURF特征描述符映射到一个统一维度的向量,即Bag of Features特征向量,再用支持向量机对图像得到的特征向量进行训练分类.实验结果表示,该方法不仅具有较高的时间效率,满足手势识别的实时性,而且即使在很大角度的旋转以及亮度的变化下,仍能达到较高的识别率.