Template Selection Algorithm Research Articles

Colour difference detection algorithm for warp‐knitted fabric based on image colour appearance model

AbstractDetecting colour differences in warp‐knitting fabric is essential to ensure its quality. Machine vision algorithms are commonly used for automatic colour difference detection. However, the current algorithm directly extracts RGB (red, green, blue) colour stimulus values from the image without considering the image's colour attributes, leading to a significant error in colour difference detection. To solve this issue, a colour appearance model is introduced into the field of colour difference detection for warp‐knitted fabric. Initially, a colour appearance model based on CAM16 is established, and the critical parameters are calculated to obtain the colour appearance attribute of the fabric. The colour difference calculation formula is then constructed in the uniform colour space of CAM16‐UCS. A template selection algorithm based on principal component analysis was designed to select warp‐knitted cloth images with standard colours. Subsequently, a cloth colour difference detection algorithm was developed using the cloth colour profile model. The performance of the colour difference formula based on the colour profile model was evaluated using the PF/3 method. To compare the CIELab, CMC(2:1), and CIEDE2000 colour difference formulas, standardised residual sum of squares was used. The results indicated that the colour difference formula based on the colour‐appearance model is about 5.32% different from the visual colour difference perceived by the human eye. However, it can perform as well as the CMC(2:1) colour difference formula, which is widely used in the textile industry.

Refined template selection and combination algorithm significantly improves template-based modeling accuracy.

In contrast to ab-initio protein modeling methodologies, comparative modeling is considered as the most popular and reliable algorithm to model protein structure. However, the selection of the best set of templates is still a major challenge. An effective template-ranking algorithm is developed to efficiently select only the reliable hits for predicting the protein structures. The algorithm employs the pairwise as well as multiple sequence alignments of template hits to rank and select the best possible set of templates. It captures several key sequences and structural information of template hits and converts into scores to effectively rank them. This selected set of templates is used to model a target. Modeling accuracy of the algorithm is tested and evaluated on TBM-HA domain containing CASP8, CASP9 and CASP10 targets. On an average, this template ranking and selection algorithm improves GDT-TS, GDT-HA and TM_Score by 3.531, 4.814 and 0.022, respectively. Further, it has been shown that the inclusion of structurally similar templates with ample conformational diversity is crucial for the modeling algorithm to maximally as well as reliably span the target sequence and construct its near-native model. The optimal model sampling also holds the key to predict the best possible target structure.

Structural regeneration of fracture-vug network in naturally fractured vuggy reservoirs

Naturally fractured vuggy carbonate reservoirs play an important role in the world's oil and gas production. Pore-scale modeling is treated as an important approach for unveiling the flow mechanism in carbonate reservoirs. The realistic regeneration of fractured vuggy reservoirs needs to preserve the geological structures and complex pores morphologies. Nevertheless, regeneration of such reservoirs is a great challenge because of the co-existence of fractures and vugs over a wide range of scales. In this paper, the reference fracture-vug network will be divided into two systems: matrix-fracture and matrix-vug. The two systems are reconstructed in two ways: (I), the matrix-vug and matrix-fracture systems are generated by improved simulated annealing method (ISAM) and multiple point statistics algorithm (MPS), respectively; (II), both of the matrix-vug and matrix-fracture systems are generated by MPS. When applying for ISAM, the multipoint histogram mainly depends on the N-point template. The template is a unit configuration, which is considered as the characteristic of the geometric features. Based on this, we introduce the correlation coefficient matrix to determine an optimal template, and the accuracy of template selection algorithm is also discussed. The optimal template represents essential geological features of the training image, and its size is much smaller than the template size selected by entropy. Therefore, it can improve the computing efficiency while preserving the key properties of the network. Then, a superimposing method is proposed to create the fracture-vug network by combining the matrix-vug with matrix-fracture models. The superimposing method using ISAM (for matrix-vug model generation) and MPS (for matrix-fracture model generation) is called SMIM, while superimposing method using MPS (for both of matrix-vug and matrix-fracture models generation) is called SMM. Finally, the spatial connectivity, local percolation probability and patterns reproduction of the generated models are used to compare with those of the reference model. The results show that the 7-point template selected by the correlation coefficient matrix is enough to get the spatial features of the matrix-vug system. The generated fracture-vug network using the selected template is able to retrieve the patterns of training image (reference model) more accurately than other used templates. The fracture-vug network generated by superimposing method produces better results than the other methods (all named as “direct method”). The network simulated with SMIM algorithm matches the reference model better than SMM algorithm. The probable reason maybe exist in the different generation methods used for matrix-vug systems. The local percolation probability (LPP), treated as a general geometric characterization method, is used to characterize the connectivity of measured units at a given local porosity. The results of the probability analysis show that SMIM is better in depicting the expected patterns of geological heterogeneities and in producing higher degree of connectivity of pore space than the SMM. The pattern reproduction of SMIM model is assessed by scanning the generated model, and the ratio of pattern reproduction number to that of reference model (i.e. the similarity) is around 97.28%. These results may guide the further application of the proposed method to field-scale modeling of naturally fractured vuggy reservoirs.

Selection of Heart-Biometric Templates for Fusion

The heart is potentially a highly secured biometric modality. Although many templates have been proposed to be extracted from heart-signal for biometric authentication, they have yet to reach a single digit equal error rate (EER) of false matches and false non-matches when applied on large across-session data sets, where gallery and probe data are taken from different sessions. However, since different templates possess different strengths, the fusion of them has a great potential to improve the authentication performance. We propose an efficient template selection algorithm to select a suitable subset of templates from a given set to obtain a minimal EER. The fusion of the subset of templates selected by this algorithm from a set of seven state-of-the-art templates has obtained a significant 5% reduction of EER in authentication in our experiments on a large database of finger-based ECG signals captured in two different sessions.

Volumetric template fitting for human body reconstruction from incomplete data

In this paper, we present a method for reconstructing 3D human body from incomplete data, which are point clouds captured by inexpensive RGB-D cameras. Making use of the volumetric mesh in a template, the fitting process is robust. This method produces high quality fitting results on incomplete data, which are hard to be offered by the surface fitting based methods. The method is formulated as an optimization procedure, so that the results of volumetric fitting rely on the quality of initial shape (i.e., the shape of template). In order to find a good initial shape, we develop a template selection algorithm to choose a template in an iterative manner by using the statistical models of human bodies. Experimental results show that our method can successfully reconstruct human body with good quality to be used in design and manufacturing applications.

Hierarchical Feature Extraction With Local Neural Response for Image Recognition

In this paper, a hierarchical feature extraction method is proposed for image recognition. The key idea of the proposed method is to extract an effective feature, called local neural response (LNR), of the input image with nontrivial discrimination and invariance properties by alternating between local coding and maximum pooling operation. The local coding, which is carried out on the locally linear manifold, can extract the salient feature of image patches and leads to a sparse measure matrix on which maximum pooling is carried out. The maximum pooling operation builds the translation invariance into the model. We also show that other invariant properties, such as rotation and scaling, can be induced by the proposed model. In addition, a template selection algorithm is presented to reduce computational complexity and to improve the discrimination ability of the LNR. Experimental results show that our method is robust to local distortion and clutter compared with state-of-the-art algorithms.

FPGA-aware techniques for rapid generation of profitable custom instructions

Instruction set extension of FPGA based reconfigurable processors provides an effective means to meet the increasingly strict design constraints of embedded systems. We have shown in our previous works [20,21] that the usage of FPGA architectural constraints for pruning the design space during enumeration of custom instructions/patterns not only leads to notable reduction in the time taken to identify custom instructions but can also result in the selection of profitable custom instructions when the area is highly constrained. However when area constraint is relaxed, the previously proposed methods failed to perform better than traditional methods. In this paper, we propose a heuristic to identify profitable custom instructions for designs with arbitrary area constraints. The proposed heuristic relies on a new pruning criterion to enumerate patterns with high size-to-hardware-area ratio. We also proposed a suitable algorithm to select profitable custom instructions from the enumerated patterns. The proposed template selection algorithm takes advantage of the FPGA area-time measures of the enumerated patterns, which can be easily inferred from the FPGA-aware enumeration strategy. Experimental results show that the proposed methods in this paper result in custom instructions that achieve an average performance gain of 76.23% over current state-of-the-art approaches.

Research of Image Registration Based on Maximum Entropy Template Selection Algorithm

This paper concerns an improved adaptive genetic algorithm, and the method is applied to the Maximum Entropy Template Selection Algorithm image registration. This method includes adjusting the probability of crossover and mutation in the evolutionary process. The method can overcome the disadvantage of traditional genetic algorithm that is easy to get into a local optimum answer. Results show our method is insensitive to the ordering, rotation and scale of the input images so it can be used in image stitching and retrieval of images & videos.

Learning Atomic Human Actions Using Variable-Length Markov Models

Visual analysis of human behavior has generated considerable interest in the field of computer vision because of its wide spectrum of potential applications. Human behavior can be segmented into atomic actions, each of which indicates a basic and complete movement. Learning and recognizing atomic human actions are essential to human behavior analysis. In this paper, we propose a framework for handling this task using variable-length Markov models (VLMMs). The framework is comprised of the following two modules: a posture labeling module and a VLMM atomic action learning and recognition module. First, a posture template selection algorithm, based on a modified shape context matching technique, is developed. The selected posture templates form a codebook that is used to convert input posture sequences into discrete symbol sequences for subsequent processing. Then, the VLMM technique is applied to learn the training symbol sequences of atomic actions. Finally, the constructed VLMMs are transformed into hidden Markov models (HMMs) for recognizing input atomic actions. This approach combines the advantages of the excellent learning function of a VLMM and the fault-tolerant recognition ability of an HMM. Experiments on realistic data demonstrate the efficacy of the proposed system.

A graph covering algorithm for a coarse grain reconfigurable system

The availability of high-level design entry tooling is crucial for the viability of any reconfigurable SoC architecture. This paper presents a graph covering algorithm. The graph covering is done in two steps: template generation and template selection. The objective of template generation step is to extract functional equivalent structures, i.e. templates, from a control data flow graph. By inspecting the graph, the algorithm generates all the possible templates and the corresponding matches. Using unique serial numbers and circle numbers, the algorithm can find all distinct templates with multiple outputs. The template selection algorithm shows how this information can be used in compilers for reconfigurable systems. The objective of the template selection algorithm is to find an efficient cover for an application graph with a minimal number of distinct templates and minimal number of matches.

Automatic target recognition and tracking using an acousto-optic image correlator

This paper discusses a hybrid electro-optic image processor, developed for automatic target recognition and tracking using an acousto-optic correlator and digital electronics. The optical system performs the computationally intensive correlation operation on the large 2-D input scenes. The electronics provide the decision-making capability and also perform part of the postprocessing needed for increasing the peak-to-clutter ratio in cluttered scenes. The system is able to analyze each correlation plane and apply a real-time template selection algorithm to accommodate scale or rotation changes of the target. A demonstration of the current system capabilities is presented using a terrain board with several different types of stationary and moving model vehicles.