Partial Matching Method Research Articles

Universe Points Representation Learning for Partial Multi-Graph Matching

Many challenges from natural world can be formulated as a graph matching problem. Previous deep learning-based methods mainly consider a full two-graph matching setting. In this work, we study the more general partial matching problem with multi-graph cycle consistency guarantees. Building on a recent progress in deep learning on graphs, we propose a novel data-driven method (URL) for partial multi-graph matching, which uses an object-to-universe formulation and learns latent representations of abstract universe points. The proposed approach advances the state of the art in semantic keypoint matching problem, evaluated on Pascal VOC, CUB, and Willow datasets. Moreover, the set of controlled experiments on a synthetic graph matching dataset demonstrates the scalability of our method to graphs with large number of nodes and its robustness to high partiality.

Monocular weakly supervised depth and pose estimation method based on multi-information fusion

The depth and pose information are the basic issues in the field of robotics, autonomous driving, and virtual reality, and are also the focus and difficult issues of computer vision research. The supervised monocular depth and pose estimation learning are not feasible in environments where labeled data is not abundant. Self-supervised monocular video methods can learn effectively only by applying photometric constraints without expensive ground true depth label constraints, which results in an inefficient training process and suboptimal estimation accuracy. To solve these problems, a monocular weakly supervised depth and pose estimation method based on multi-information fusion is proposed in this paper. First, we design a high-precision stereo matching method to generate a depth and pose data as the "Ground Truth" labels to solve the problem that the ground truth labels are difficult to obtain. Then, we construct a multi-information fusion network model based on the "Ground truth" labels, video sequence, and IMU information to improve the estimation accuracy. Finally, we design the loss function of supervised cues based on "Ground Truth" labels cues and self-supervised cues to optimize our model. In the testing phase, the network model can separately output high-precision depth and pose data from a monocular video sequence. The resulting model outperforms mainstream monocular depth and poses estimation methods as well as the partial stereo matching method in the challenging KITTI dataset by only using a small number of real training data(200 pairs).

An Empirical Evaluation of Prediction by Partial Matching in Assembly Assistance Systems

Industrial assistive systems result from a multidisciplinary effort that integrates IoT (and Industrial IoT), Cognetics, and Artificial Intelligence. This paper evaluates the Prediction by Partial Matching algorithm as a component of an assembly assistance system that supports factory workers, by providing choices for the next manufacturing step. The evaluation of the proposed method was performed on datasets collected within an experiment involving trainees and experienced workers. The goal is to find out which method best suits the datasets in order to be integrated afterwards into our context-aware assistance system. The obtained results show that the Prediction by Partial Matching method presents a significant improvement with respect to the existing Markov predictors.

Preventing the Video Leakages from The Traffic Streaming

Video streaming takes up an increasing proportion of network traffic nowadays. Dynamic Adaptive Streaming over HTTP (DASH) becomes the defacto standard of video streaming and it is adopted by YouTube, Netflix, etc.Despite of the popularity, network traffic during video streaming shows identifiable pattern which brings threat to user privacy.In this paper, to proposea video identification method using network traffic while streaming. Though there is bitrate adaptation in DASH streaming, we observe that the video bit rate trend remains relatively stable because of the widely used Variable Bit-Rate(VBR) encoding. Accordingly, we design a robust video feature extraction method for eavesdropped video streaming traffic. Meanwhile, we design a VBR based video fingerprinting method for candidate video set which can be built using downloaded video files. Finally, to propose an efficient partial matching method for computing similarities between video fingerprints and streaming traces to derive video identities. To evaluate our attack method in different scenarios for various video content, segment lengths and quality levels. The experimental results show that the identification accuracy can reach up to 90%using only three minute continuous network traffic eavesdropping.

Geophysical investigation of foundation failure at Medina Estate, Lagos, Southwestern Nigeria

Integrated geophysical investigation involving Ground Penetrating Radar (GPR) and Electrical Resistivity methods were carried out at Medina Estate, Lagos southwestern Nigeria to map the subsurface lithology in order to delineate its peat stratigraphy that has been causing foundation failure in the area. Twenty-one traverses (varying from 35-880 m in length) of Ground Penetrating Radar (GPR) survey were conducted along the streets of Medina trending NE-SW and NW-SE directions using the Mala 250 MHZ bi-static shielded antenna. Thirty-six Vertical Electrical Soundings (VES) were carried out using Schlumberger electrode array at some selected points along the established traverses within the area. The GPR data were processed into radar section using Rad Explorer software. The VES data were interpreted quantitatively using the partial curve matching method and 1-D forward modeling with Win Resist Software. Available litho-logs from boreholes drilled within the area were compared with the geophysical results. Results of the GPR survey delineated three geologic layers which include the topsoil with high amplitude, parallel to sub parallel, horizontal reflections, with thickness varying from 1 to 2 m across the entire profiles and composed of lateritic clay; peat layer with low amplitude, parallel sinuous/wavy reflections with depth of occurrence ranging from 2.0 to 8 m and clay with low amplitude, planar, horizontal, sub-parallel reflections underlying the peat layer. Vertical Electrical Sounding results revealed the presence of three geological layers which are the topsoil, peat and clay and sandy clay with layer resistivity values ranging from 20- 225 Ωm, 5 – 90 Ωm and 36 to 366 Ωm and thickness values ranging from 0.5 – 2 m, 4.0-29.0 m and infinity respectively. Borehole information confirms the occurrence of shallow peat with depth ranging from 1.5 to 9 m and clay layer with depth ranging from 9 to 21 m beneath the area. The GPR survey results correlates with the well logs acquired in the study area. Based on the correlation of the geophysical results with the well logs, the GPR gives better information about the peat layer compared to the Electrical ResistivityMethod. The information obtained from this study shows that the soils at shallow depth are organic soils which are difficult foundation materials because they exhibit very high compressibility, as such making shallow foundation impossible except some form of soil improvement is carried out. The alternative approach is the adoption of deep foundations in form of piles.
 Keywords: Foundation Failure, Geophysical Investigation, Ground Penetrating Radar, Vertical Electrical Sounding, Peat.

Traffic-Based Side-Channel Attack in Video Streaming

Video streaming takes up an increasing proportion of network traffic nowadays. Dynamic adaptive streaming over HTTP (DASH) becomes the de facto standard of video streaming and it is adopted by Youtube, Netflix, and so on. Despite of the popularity, network traffic during video streaming shows an identifiable pattern which brings threat to user privacy. In this paper, we propose a video identification method using network traffic while streaming. Though there is bitrate adaptation in DASH streaming, we observe that the video bitrate trend remains relatively stable because of the widely used variable bit-rate (VBR) encoding. Accordingly, we design a robust video feature extraction method for eavesdropped video streaming traffic. Meanwhile, we design a VBR-based video fingerprinting method for candidate video set which can be built using downloaded video files. Finally, we propose an efficient partial matching method for computing similarities between video fingerprints and streaming traces to derive video identities. We evaluate our attack method in different scenarios for various video content, segment lengths, and quality levels. The experimental results show that the identification accuracy can reach up to 90% using only three-minute continuous network traffic eavesdropping.

A 3GS/s 12-bit Current-Steering Digital-to-Analog Converter (DAC) in 55 nm CMOS Technology

A 3GS/s 12-bit current-steering digital-to-analog converter (DAC) fabricated in 55 nm complementary metal–oxide–semiconductor (CMOS) technology has been presented. A partial randomization dynamic element matching (PRDEM) method based on switching sequence optimization is proposed to mitigate the mismatch effect and suppress the harmonic distortion with low hardware complexity. In the switching current cell, the cascode structure together with “always-ON” small current sources are used to keep the output impedance high and uniform. A compact layout of the switching current array is carefully designed, featuring short wires routing and small parasitic capacitance. According to the measured results at 3GS/s, this DAC demonstrates a spurious-free dynamic range (SFDR) of 74.64 dBc at low frequency and 50 dBc at 1.5 GHz output. The chip occupies an active area of 0.2 × 0.48 mm2 and consumes a total power of 495 mW.

Feature Curve Co‐Completion in Noisy Data

AbstractFeature curves on 3D shapes provide important hints about significant parts of the geometry and reveal their underlying structure. However, when we process real world data, automatically detected feature curves are affected by measurement uncertainty, missing data, and sampling resolution, leading to noisy, fragmented, and incomplete feature curve networks. These artifacts make further processing unreliable. In this paper we analyze the global co‐occurrence information in noisy feature curve networks to fill in missing data and suppress weakly supported feature curves. For this we propose an unsupervised approach to find meaningful structure within the incomplete data by detecting multiple occurrences of feature curve configurations (co‐occurrence analysis). We cluster and merge these into feature curve templates, which we leverage to identify strongly supported feature curve segments as well as to complete missing data in the feature curve network. In the presence of significant noise, previous approaches had to resort to user input, while our method performs fully automatic feature curve co‐completion. Finding feature reoccurrences however, is challenging since naïve feature curve comparison fails in this setting due to fragmentation and partial overlaps of curve segments. To tackle this problem we propose a robust method for partial curve matching. This provides us with the means to apply symmetry detection methods to identify co‐occurring configurations. Finally, Bayesian model selection enables us to detect and group re‐occurrences that describe the data well and with low redundancy.

A novel clustering algorithm of extracting road network from low-frequency floating car data

Keeping the digital road maps up-to-date is of critical importance, because the quality of many road-dependent services relies on it, but traditional measurement methods are still time-consuming and expensive. With the GPS technology and wireless communication technology maturing, the positioning data from floating car become a new data source for updating road maps. The paper presents a novel incremental clustering algorithm for automatically extracting the topology of the road network employing the floating car data. A trajectory is selected as a road Link and then the remaining trajectories are added in turn until all tracks are processed. Further, the algorithm determines whether to merge the trajectory or divide it into a new Link by judging the relations of the space position between the newly added trajectory and the existing Link. A partial curve matching method based on Frechet distance is employed to measure the partial similarity between a Trajectory and a Link and the time complexity of the proposed algorithm is reduced. Experiments show that the algorithm can quickly extract the geometric shape and topology of the road network with lightweight floating car data.

Hydro-Geophysical Assessment of Groundwater Resources Within Parts of Omu Aran, South Western Nigeria

Hydro-geophysical assessment of groundwater resources in part of Omu Aran South Western Nigeria has been evaluated and analyzed with a view of delineating the groundwater potentials and aquifer characteristics within the study area. Eleven-(11) vertical electrical soundings (VES) were acquired with a maximum half current electrode spacing of 75 metres using ABEM 3000 SAS Tetrameter and the sounding data were processed and interpreted using partial curve matching method by the computer iteration techniques. Results from the geo-electric sections revealed the presence of three to five geo-electric layers. The depth to water table ranges between 2.59m and 71.9m and a resistivity of 89.9 to 3072 Ωm. The depth to Watertable is deepest around Omu area with depth of 71.9m. The result of the geophysical analysis correlates positively with themselves showing similarity in geology. The result shows that the weathered basement is a primary target for ground water exploration in the studied area, as the area is void of prominent fracture which is a target for ground water exploration. It is recommended that an average depth of 7.0m should be drilled for borehole within the northern part of the studied area and a depth of about 10.0m in the southern part of the study area. All these deductions were reached after qualitative and quantitative interpretation of the geophysical data, and considering geology of the area.

Partial fingerprint identification for large databases

Nowadays, most fingerprint sensors capture partial fingerprint images. Incomplete, fragmentary, or partial fingerprint identification in large databases is an attractive research topic and is remained as an important and challenging problem. Accordingly, conventional fingerprint identification systems are not capable of providing convincing results. To overcome this problem, we need a fast and accurate identification strategy. In this context, fingerprint indexing is commonly used to speed up the identification process. This paper proposes a robust and fast identification system that combines two indexing algorithms. One of the indexing algorithms uses minutiae triplets, and the other uses orientation field (OF) to index and retrieve fingerprints. Furthermore, the proposal uses some partial fingerprint matching methods on final candidate list obtained from the indexing stage. The proposal is evaluated over two national institutes of standards and technology (NIST) datasets and four fingerprint verification competition (FVC) datasets leading to low identification times with no accuracy loss.

Classifying fragments of terracotta warriors using template-based partial matching

Large numbers of Terracotta Warriors fragments are mixed up when they are excavated, which calls the need for classifying them in order to avoid one to all matches and improve the efficiency of reassembly. In this paper, we propose a novel template-based classification algorithm for Terracotta Warriors fragments, which transforms the problem of classification into the problem of partial shape matching. Firstly, a few distinct regions, which indicate categories of the fragments, are selected as templates from collections of fragments. Secondly, a novel partial matching procedure is proposed to find whether a fragment have a sub-region that is similar to one of the templates. If there exists a sub-region on the fragment that is similar to one of the templates, this fragment is considered to belong to the category that the matching template represents. The partial matching procedure consists of a coarse matching and a fine matching, which utilizes the normal distribution descriptor and the modified point feature histogram descriptor, respectively. The normal distribution descriptor characterizes the structure of a Euclidean-sphere region and the modified point feature histogram descriptor characterizes the structure of a geodesic-disk region. Experiments have been conducted on Terracotta Warriors fragments that are scanned from real sites to verify the effectiveness of our method. Comparing with other partial matching methods, more accurate classification results are achieved.

A novel method for 2D nonrigid partial shape matching

Abstract There are two categories of partial shape matching problem: whole-to-part matching and part-to-part matching. The first establishes the best match between an open curve and a part of a closed curve, while the second is to find a part of the first input closed curve that can be well aligned with a part of the second input closed curve. In this paper, we present a novel approach to solve these two categories of the partial shape matching problem. First, we propose a novel shape descriptor, triangular centroid distances (TCDs), for shape representation; the TCDs shape descriptor is invariant to translation, rotation, scaling, and considerable shape deformations. Then, using the TCDs shape descriptor, we present a method to deal with the whole-to-part partial shape matching problem. Finally, we extend our work to part-to-part partial shape matching. Here, we propose a new approach, again using the TCDs shape descriptor, to solve the part-to-part partial shape matching problem. Experimental results demonstrate that our method outperforms existing methods in 2D nonrigid partial shape matching.

Electrical resistivity investigation of the groundwater potential in parts of Kwara State Polytechnic, Ilorin, Nigeria

Vertical Electrical Soundings (VES) were carried out within the premises of the Institute of Technology, Kwara State Polytechnic Campus, Ilorin Kwara State, Nigeria, with the aim of determining viable aquiferous zones within the institute to alleviate the problems of well failure in the area. The study area is about 1.5kmsqures and is underlain by the Precambrian basement rocks comprising migmatite gneiss. Fifteen (15) VES were carried out using Schlumberger electrode arrayconfiguration with AB/2 equal to 70m. The VES data generated were processed and interpreted using partial curve matching method and computer iteration techniques. The interpreted data revealed three to four geo-electric sections with varied thicknesses and resistivity. The lateritic clay layer ranges from 53.1 to 302Ωm, the weathered horizon resistivity ranges from 22.7 to474.2Ωm while the competent rock has resistivity values greater than 220.3Ωm. The lateritic clay layer resistivity and thickness range from 53.1 to 302Ωm and 1.9 to 8.0m respectively, the weathered horizon resistivity ranges from 22.7 to 474.2Ωm and 4.4 to 11.7m respectively while the competent rock has resistivity values greater than 220.3Ωm and 6.1 to ∞m respectively. The third geoelectric layer constitutes the aquiferous zone in the 4-layer geoelectric section while the second geoelectric layer is the aquiferous zone in all the 3-layer geoelectric sections. Only VES station 9 out of the 15 VES stations shows good groundwater potential as revealed by the thick overburden and weathered layer with low resistivity value. VES stations 3, 4, and 13 show poor groundwater potentials while the others are non-aquifereous in nature.

Robust partial fingerprint recognition using wavelet SIFT descriptors

Even though there have been many advancements in the fingerprint identification, matching of the partial and overlapped fingerprints is yet to be resolved. This problem has drawn more attention with the evolution of small-sized scanners. The research attempts to resolve this issue whenever there are no core points available in the partial fingerprints. Moreover, the scaled or rotated versions of the image may also lead to poor matching performance. In order to overcome these challenges, a robust partial fingerprint matching method using the scale-invariant feature transform (SIFT) features of the wavelet decomposed image is proposed. The performance of the proposed method is compared with the baseline (minutiae) and the state-of-the-art (SIFT) techniques for partial fingerprint recognition. The method is experimented for different cropped levels (horizontal, vertical, diagonal, quadrant-wise random cuts and the region around a core point) of the image. Experimental studies with 100 subjects show that the proposed method improves recognition accuracy and reduces false acceptance rate (FAR) and false rejection rate (FRR) even for images with 75% occlusion.

Boundary image matching supporting partial denoising using time-series matching techniques

In this paper, we deal with the problem of boundary image matching which finds similar boundary images regardless of partial noise exploiting time-series matching techniques. Time-seris matching techniques make it easier to compute distances for similarity identification, and therefore it is feasible to perform boundary image matching even on a large image database. To solve this problem, we first convert all boundary images into times-series and derive partial denoising time-series. The partial denoising time-series is generated from an original time-series by removing partial noise; that is, it is obtained by changing a position of partial denoising from original time-series. We then introduce the partial denoising distance, which is the minimum distance from a query time-series to all possible partial denoising time-series generated from a data time-series, and propose partial denoising boundary image matching using the partial denoising distance as a similarity measure. Computing the partial denoising distance, however, incurs a severe computational overhead since there are a large number of partial denoising time-series to be considered. Thus, in order to improve its performance, we present a tight lower bound of the partial denoising distance and also optimize the computation of the partial denoising distance. We finally propose range and k-NN query algorithms according to a query processing method for partial denoising boundary image matching. Through extensive experiments, we show that our lower bound-based approach and the optimization method of the partial denoising distance improve search performance by up to an order of magnitude.

Interactive partial 3D shape matching with geometric distance optimization

In this paper, we propose an efficient method for partial 3D shape matching based on minimizing the geometric distance between the source and the target geometry. Unlike existing methods, our method does not use a feature-based distance in order to obtain a matching score. Instead, we use a fast, GPU-based method to approximate the true geometric distance between the source and the target by rendering the source object into a distance field which was built around the target. This function behaves smoothly in the space of transformations and allows for an efficient gradient-based local optimization. In order to overcome local minima, we use single point correspondences between surface points on the source and the target respectively employing simple, yet efficient local features based on the distribution of normal vectors around a reference point. The best correspondences define starting positions for a local optimization. The high efficiency of the distance computation allows for robust determination of the global minima in less than a second, which makes our method usable in interactive applications. Our method works for any kind of input data since it only requires point data with normal information at each point. We also demonstrate the capability of our algorithm to perform global alignment of similar 3D objects.

Similarity invariant partial shape matching using coarse-to-fine strategy

The matching between an open contour and a closed contour is a basis for the alignment of their common part and a similarity measure. We propose a coarse-to-fine method for partial shape matching, which does not need to scan the target shape, construct a codebook of model contour fragments, or depend on background support domains. For this purpose, a linearization algorithm for partial shapes is introduced to extract the initial shape segments from the closed contour those possibly match with the open contour. The next refining procedure of the coarse matching eliminates significantly dissimilar shape segments to reduce the further processing of fine matching. We propose a shape similarity description to finely describe the similarity between the open contour and the remaining shape segments. Finally, an order-preserving point injection between the open contour and the closed contour is established. Valuations of the proposed method on a benchmark dataset and real images demonstrate that the overall and component performances are excellent and robust to various disturbances and similarity transformations. Last, a gesture recognition application is implemented.

Partial matching of 3D cultural heritage objects using panoramic views

In this paper, we present a method for partial matching and retrieval of 3D objects based on range image queries. The proposed methodology addresses the retrieval of complete 3D objects using range image queries that represent partial views. The core methodology relies upon Bag-of-Visual-Words modelling and enhanced Dense SIFT descriptor computed on panoramic views and range image queries. Performance evaluation builds upon standard measures and a challenging 3D pottery dataset originating from the Hampson Archaeological Museum collection.

Novel affine‐invariant curve descriptor for curve matching and occluded object recognition

The authors present a new approach for affine distorted planar curve matching and exploit it for occluded object recognition. There are two main contributions in the study: First, a novel affine‐invariant curve descriptor (AICD) based on a new‐defined affine‐invariant signature and its unsigned sum is proposed to represent the local shape of a curve with high distinctiveness. Second, a part‐to‐part curve matching algorithm is developed by combining AICD with a curve segmentation strategy based on inflexion points, which can be applied to object recognition under affine distortions and partial occlusions. Experimental results demonstrate that the proposed method exhibits effectiveness in occluded object recognition better than the state‐of‐the‐art partial curve matching methods.