Spatial Segmentation Algorithm Research Articles

Spatial attributes-based segmentation and topological attributes-based recognition algorithm for Myanmar OCR

Spatial attributes-based segmentation and topological attributes-based recognition algorithm for Myanmar OCR

A Markov Chain Monte Carlo Algorithm for Spatial Segmentation

Spatial data are very often heterogeneous, which indicates that there may not be a unique simple statistical model describing the data. To overcome this issue, the data can be segmented into a number of homogeneous regions (or domains). Identifying these domains is one of the important problems in spatial data analysis. Spatial segmentation is used in many different fields including epidemiology, criminology, ecology, and economics. To solve this clustering problem, we propose to use the change-point methodology. In this paper, we develop a new spatial segmentation algorithm within the framework of the generalized Gibbs sampler. We estimate the average surface profile of binary spatial data observed over a two-dimensional regular lattice. We illustrate the performance of the proposed algorithm with examples using artificially generated and real data sets.

Automatic “Ground Truth” Annotation and Industrial Workpiece Dataset Generation for Deep Learning

In industry, it is becoming common to detect and recognize industrial workpieces using deep learning methods. In this field, the lack of datasets is a big problem, and collecting and annotating datasets in this field is very labor intensive. The researchers need to perform dataset annotation if a dataset is generated by themselves. It is also one of the restrictive factors that the current method based on deep learning cannot expand well. At present, there are very few workpiece datasets for industrial fields, and the existing datasets are generated from ideal workpiece computer aided design (CAD) models, for which few actual workpiece images were collected and utilized. We propose an automatic industrial workpiece dataset generation method and an automatic ground truth annotation method. Included in our methods are three algorithms that we proposed: a point cloud based spatial plane segmentation algorithm to segment the workpieces in the real scene and to obtain the annotation information of the workpieces in the images captured in the real scene; a random multiple workpiece generation algorithm to generate abundant composition datasets with random rotation workpiece angles and positions; and a tangent vector based contour tracking and completion algorithm to get improved contour images. With our procedures, annotation information can be obtained using the algorithms proposed in this paper. Upon completion of the annotation process, a json format file is generated. Faster R-CNN (Faster R-convolutional neural network), SSD (single shot multibox detector) and YOLO (you only look once: unified, real-time object detection) are trained using the datasets proposed in this paper. The experimental results show the effectiveness and integrity of this dataset generation and annotation method.

Spatial Possibilistic Fuzzy C-Mean Segmentation Algorithm Integrated with Brain Mid-sagittal Surface Information

A normal human brain holds a high level of bilateral reflection symmetry. On the sagittal view, the brain can be separated into the left and the right hemispheres with approximately identical anatomical properties, so that symmetric mirror pixels have similar properties. As a result, the symmetry information can be used to enhance results of brain segmentation methods. In this paper, we introduced a new version of the Fuzzy C-Mean segmentation method, Symmetry Spatial Possibilistic FCM. SymSPFCM integrates symmetry information with SPFCM which is an extension of PFCM on 3D MR images, and uses the spatial information to calculate possibilistic values and fuzzy membership values. We added spatial and possibilistic information in order to solve the noise sensibility defect of FCM. To integrate the symmetry information, we first extracted the mid-sagittal surface using our proposed method. According to this method, inside each axial slice, a thin-plate spline surface was constructed and local optima were applied to fit this TPS surface to the brain data. Then, the symmetry degree of each symmetry pair was calculated. Finally, the membership values in SPFCM were updated based on the corresponding symmetric values. The efficiency of the proposed method, SymSPFCM, was evaluated using both simulated and real magnetic resonance images and was compared to the state-of-the-art methods. Our results showed images with different degrees of intensity non-uniformity and different levels of noise were segmented efficiently by the SymSPFCM.

Can spectral-spatial image segmentation be used to discriminate experimental burn wounds?

Hyperspectral imaging (HSI) is a noncontact and noninvasive optical modality emerging the field of medical research. The goal of this study was to determine the ability of HSI and image segmentation to discriminate burn wounds in a preclinical porcine model. A heated brass rod was used to introduce burn wounds of graded severity in a pig model and a sequence of hyperspectral data was recorded up to 8-h postinjury. The hyperspectral images were processed by an unsupervised spectral–spatial segmentation algorithm. Segmentation was validated using results from histology. The proposed algorithm was compared to K-means segmentation and was found superior. The obtained segmentation maps revealed separated zones within the burn sites, indicating a variation in burn severity. The suggested image-processing scheme allowed mapping dynamic changes of spectral properties within the burn wounds over time. The results of this study indicate that unsupervised spectral–spatial segmentation applied on hyperspectral images can discriminate burn injuries of varying severity.

A Spatial Segmentation Algorithm for Resource Allocation in an Integrated Spatial and Networked Environment

We examine the discrete shortest path network interdiction problem and introduce an algorithm to determine defense resource location points based on network properties. Our proposed method examines how network density, complexity and connectivity can be used to establish improved discrete geographic locations for allocating defense resources. We test performance of the algorithmically-derived locations on the real-world sub-networks of Washington DC, Houston and New York City and compare the resulting discrete shortest path network interdiction results to three grid-based location schemes using computational and spatial analysis techniques. Results demonstrate improved objective performance and a high degree of spatial dissimilarity between the algorithmic and grid-based location schemes. The observed dissimilarity illustrates the importance of strong resource location identification schemes and the propensity for erroneous decision-making under simplified resource location assumptions.

Spatial normalization of array-CGH data.

BackgroundArray-based comparative genomic hybridization (array-CGH) is a recently developed technique for analyzing changes in DNA copy number. As in all microarray analyses, normalization is required to correct for experimental artifacts while preserving the true biological signal. We investigated various sources of systematic variation in array-CGH data and identified two distinct types of spatial effect of no biological relevance as the predominant experimental artifacts: continuous spatial gradients and local spatial bias. Local spatial bias affects a large proportion of arrays, and has not previously been considered in array-CGH experiments.ResultsWe show that existing normalization techniques do not correct these spatial effects properly. We therefore developed an automatic method for the spatial normalization of array-CGH data. This method makes it possible to delineate and to eliminate and/or correct areas affected by spatial bias. It is based on the combination of a spatial segmentation algorithm called NEM (Neighborhood Expectation Maximization) and spatial trend estimation. We defined quality criteria for array-CGH data, demonstrating significant improvements in data quality with our method for three data sets coming from two different platforms (198, 175 and 26 BAC-arrays).ConclusionWe have designed an automatic algorithm for the spatial normalization of BAC CGH-array data, preventing the misinterpretation of experimental artifacts as biologically relevant outliers in the genomic profile. This algorithm is implemented in the R package MANOR (Micro-Array NORmalization), which is described at and available from the Bioconductor site . It can also be tested on the CAPweb bioinformatics platform at .

Unsupervised spatiotemporal segmentation algorithm for on-chip video systems

An efficient moving-object segmentation algorithm suitable for implementing on a chip is proposed. The basic idea is to use simultaneously a novel spatial segmentation algorithm and an effective temporal algorithm based on the accumulative information technique to produce the video objects. First, the spatial and the temporal segmentation algorithms are used simultaneously to produce the edges and the region of a moving object, respectively. Then, we make use of the edges with the region to obtain the object. It is found that the number of time-consuming motion estimation computations can be reduced dramatically. Hence, the overall processing speed is significantly accelerated to meet the hardware implementation requirement. Finally, a postprocessing step is applied to the object to smooth the object boundary. Good performance of this algorithm is demonstrated by experimental results.

A microcomputer-based solid-state nuclear track image analyzer

A microcomputer-based image processing system has been developed to use with solid-state nuclear track detectors for number counting, area measurement, and location identification. The image digitizer is designed to interface with a microcomputer and a standard black and white TV camera for data acquisition. A spatial dependent segmentation algorithm is proposed for track identification under nonuniform illumination and the low track-pixel population conditions. The system has been tested using Lexan samples irradiated by a Cf-252 spontaneous fission source. The counting accuracy is approximately 3% with a long term stability of 5%. Efficiency calibration was performed using samples with track densities up to 104/mm2. Results indicate that the proposed track identification scheme tends to reduce the track overlap effect and the system behaves as a nonparalyzable counting system. For track densities below 3000/mm2, either a paralyzable or a nonparalyzable counter model can be established with an accuracy better than 0.5%. For track densities below 1500/mm2, the track registration efficiency is in good agreement with manual counting results.

Estimation Of Ship Profiles From A Time Sequence Of Forward-Looking Infrared Images

This paper addresses the problem of estimating the profile, or silhouette, of a ship target from a sequence of forward-looking infrared (FLIR) imagery obtained at video rates. We are specifically interested in the performance of multiframe processing techniques compared with single-frame methods. Our approach to multiframe signal processing combines spatial and temporal processing in two stages: first, a target profile is extracted from each image frame by a segmentation algorithm; second, the resulting sequence of profiles is temporally filtered in order to increase the signal-to-noise ratio. Long sequences of FLIR imagery tend to exhibit several characteristic forms of non-Gaussian noise (random speckle, occlusions, and flaring) caused by various atmospheric and background phenomena, as well as instrument noise. Simple temporal averaging is inadequate in this environment. In this paper we develop a combination of spatial and temporal processing algorithms that may be used to overcome the signal-to-noise ratio problems associated with these noise effects. A recursive temporal median filter in conjunction with a simple spatial segmentation algorithm is proposed for this purpose. Experimental results based on a database of FLIR ship imagery are presented in support of the spatiotemporal processor. Although the approach is developed for ship targets, we feel it could be adapted for a broader class of FLIR applications.