Abstract:Abstract. An improved and general approach to connected-component labeling of images is presented. The algorithm presented in this paper processes images in predeterttuned order, which means that the processing order depends only on the image representation scheme and not on specific properties of the image. The algorithm handles a wide variety of image representation schemes (rasters, run lengths, quadtrees, bintrees, etc.). How to adapt the standard UNION-FIND algorithm to permit reuse of tempora~labels is s… Show more
“…The isolated components which are included in upper and lower zones are segmented using connected component (CC) analysis [36] and next they are recognized and labelled as text characters. After resizing the images to 150x150, here also PHOG feature of vector length 168 is extracted from the components of upper and lower zone modifiers.…”
Section: B Upper/lower Zone Modifier Modeling Using Svmmentioning
Handwritten word recognition and spotting of low-resource scripts are difficult as sufficient training data is not available and it is often expensive for collecting data of such scripts. This paper presents a novel cross language platform for handwritten word recognition and spotting for such low-resource scripts where training is performed with a sufficiently large dataset of an available script (considered as source script) and testing is done on other scripts (considered as target script). Training with one source script and testing with another script to have a reasonable result is not easy in handwriting domain due to the complex nature of handwriting variability among scripts. Also it is difficult in mapping between source and target characters when they appear in cursive word images. The proposed Indic cross language framework exploits a large resource of dataset for training and uses it for recognizing and spotting text of other target scripts where sufficient amount of training data is not available. Since, Indic scripts are mostly written in 3 zones, namely, upper, middle and lower, we employ zone-wise character (or component) mapping for efficient learning purpose. The performance of our crosslanguage framework depends on the extent of similarity between the source and target scripts. Hence, we devise an entropy based script similarity score using source to target character mapping that will provide a feasibility of cross language transcription. We have tested our approach in three Indic scripts, namely, Bangla, Devanagari and Gurumukhi, and the corresponding results are reported.
“…The isolated components which are included in upper and lower zones are segmented using connected component (CC) analysis [36] and next they are recognized and labelled as text characters. After resizing the images to 150x150, here also PHOG feature of vector length 168 is extracted from the components of upper and lower zone modifiers.…”
Section: B Upper/lower Zone Modifier Modeling Using Svmmentioning
Handwritten word recognition and spotting of low-resource scripts are difficult as sufficient training data is not available and it is often expensive for collecting data of such scripts. This paper presents a novel cross language platform for handwritten word recognition and spotting for such low-resource scripts where training is performed with a sufficiently large dataset of an available script (considered as source script) and testing is done on other scripts (considered as target script). Training with one source script and testing with another script to have a reasonable result is not easy in handwriting domain due to the complex nature of handwriting variability among scripts. Also it is difficult in mapping between source and target characters when they appear in cursive word images. The proposed Indic cross language framework exploits a large resource of dataset for training and uses it for recognizing and spotting text of other target scripts where sufficient amount of training data is not available. Since, Indic scripts are mostly written in 3 zones, namely, upper, middle and lower, we employ zone-wise character (or component) mapping for efficient learning purpose. The performance of our crosslanguage framework depends on the extent of similarity between the source and target scripts. Hence, we devise an entropy based script similarity score using source to target character mapping that will provide a feasibility of cross language transcription. We have tested our approach in three Indic scripts, namely, Bangla, Devanagari and Gurumukhi, and the corresponding results are reported.
“…Connected component labelling [16], with 8-connected neighbourhoods, is performed on the contour map and a connected component is obtained for each continuous contour. The Moore-Neighbour tracing algorithm with Jacob's stopping criteria [28] is applied to each component to provide sequences of points.…”
Section: B Producing the Segment Maps 1) Traversing A Contourmentioning
Abstract-Dong et al. examined the ability of 51 computational feature sets to estimate human perceptual texture similarity, however, none performed well for this task. While it is well-known that the human visual system is extremely adept at exploiting longer-range aperiodic (and periodic) "contour" characteristics in images, none of the investigated feature sets exploit higher order statistics (HOS) over larger image regions (>19×19 pixels). We therefore hypothesise that long-range HOS, in the form of contour data, are useful for perceptual texture similarity estimation.We present the results of a psychophysical experiment that shows that contour data are more important, than local image patches, or global 2nd-order data, to human observers for this task.Inspired by this finding, we propose a set of perceptually motivated image features (PMIF) that encode the long-range HOS computed from spatial and angular distributions of contour segments. We use two perceptual texture similarity estimation tasks to compare PMIF against the 51 feature sets referred to above and four commonly used contour representations. This new feature set is also examined in the context of two additional tasks: sketch-based image retrieval and natural scene recognition. The results show that the proposed feature set performs better, or at least comparably to, all the other feature sets. We attribute this promising performance to the fact that the proposed feature set exploits both short-range and long-range HOS.
“…The core of the non-iterative SIAM software pipeline is a one-pass prior knowledge-based decision tree (expert system) for MS reflectance space hyperpolyhedralization (quantization, partitioning) into static (non-adaptive-to-data) color names, see Figure 2 and refer to Chapter 2 and Chapter 3 in the Part 1. Presented in the RS literature where enough information was provided for the implementation to be reproduced (Baraldi et al, 2006), the SIAM expert system for MS color naming is followed by a well-posed two-pass superpixel detector in the multi-level color map-domain (Dillencourt, Samet, & Tamminen, 1992; Sonka, Hlavac, & Boyle, 1994) and a per-pixel VQ error assessment for VQ quality assurance, in agreement with the GEO-CEOS QA4EO Val guidelines, refer to Figure 4 in the Part 1 of this paper.…”
ESA defines as Earth Observation (EO) Level 2 information product a multi-spectral (MS) image corrected for atmospheric, adjacency, and topographic effects, stacked with its data-derived scene classification map (SCM), whose legend includes quality layers cloud and cloud-shadow. No ESA EO Level 2 product has ever been systematically generated at the ground segment. To fill the information gap from EO big data to ESA EO Level 2 product in compliance with the GEO-CEOS stage 4 validation (Val) guidelines, an off-the-shelf Satellite Image Automatic Mapper (SIAM) lightweight computer program was selected to be validated by independent means on an annual 30 m resolution Web-Enabled Landsat Data (WELD) image composite time-series of the conterminous U.S. (CONUS) for the years 2006 to 2009. The SIAM core is a prior knowledge-based decision tree for MS reflectance space hyperpolyhedralization into static (non-adaptive to data) color names. For the sake of readability, this paper was split into two. The present Part 2—Validation—accomplishes a GEO-CEOS stage 4 Val of the test SIAM-WELD annual map time-series in comparison with a reference 30 m resolution 16-class USGS National Land Cover Data (NLCD) 2006 map. These test and reference map pairs feature the same spatial resolution and spatial extent, but their legends differ and must be harmonized, in agreement with the previous Part 1 - Theory. Conclusions are that SIAM systematically delivers an ESA EO Level 2 SCM product instantiation whose legend complies with the standard 2-level 4-class FAO Land Cover Classification System (LCCS) Dichotomous Phase (DP) taxonomy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.