Interactive on-line perception of line patterns

A software Pattern Perception System, PPS, motivated by human perceptive characteristics, is developed to recognize and classify complex line patterns. This paper presents the functional organization of PPS, as well as relevant psychological observations. The data structure and processing methodology involved are also illustrated with a sample pattern. Recursive patterns are treated, specifically their representation and generation.

2018

The purpose of perceptual grouping is to organize image data in a scene without the aid of semantic knowledge. The resulting groups identify significant structural relationships which are helpful in scene interpretation. The perceptual organization process starts with the primitives or tokens obtained from the images and groups "similar" tokens. It groups dots into blobs, blobs into larger blobs, edge segments into longer curves or complex structures, etc. The similarity among tokens is defined in terms of intrinsic properties of primitives and their spatial relationship in the image plane. Previous work closely related to grouping and extraction of perceptual structure in vision includes the clustering of d-dimensional dot patterns,3,2, 1, 13 the orientation detection in glass patterns12,8 and dot patterns,19,20,21 the extraction of structure from a raw primal sketch,7,6, 15 and clustering of one-dimensional line segments.4, 10 The principles of perceptual organization, w...

2005

Many shape recognition techniques have been presented in literature, most of them from a quantitative perspective. Research has shown that qualitative reasoning better reflects the way humans deal with spatial reality. The current qualitative techniques are based on break points resulting in difficulties in comparing analogous relative positions along polylines. The presented shape representation technique is a qualitative approach based on division points, resulting in shape matrices forming a shape data model and thus forming the basis for a cognitively relevant similarity measure for shape representation and shape comparison, both locally and globally.

Pattern Analysis and Machine …, 1999

AbstractÐThis paper presents a new compact shape representation for retrieving line-patterns from large databases. The basic idea is to exploit both geometric attributes and structural information to construct a shape histogram. We realize this goal by computing the N-nearest neighbor graph for the lines-segments for each pattern. The edges of the neighborhood graphs are used to gate contributions to a two-dimensional pairwise geometric histogram. Shapes are indexed by searching for the line-pattern that maximizes the cross correlation of the normalized histogram bin-contents. We evaluate the new method on a database containing over 2,500 line-patterns each composed of hundreds of lines.

Computer vision and image Understanding, 1998

A generic integrated line detection algorithm (GILDA) is presented and demonstrated. GILDA is based on the generic graphics recognition approach, which abstracts the graphics recognition as a stepwise recovery of the multiple components of the graphic objects and is specified by the object-process methodology. We define 12 classes of lines which appear in engineering drawings and use them to construct a class inheritance hierarchy. The hierarchy highly abstracts the line features that are relevant to the line detection process. Based on the "Hypothesis and Test" paradigm, lines are detected by a stepwise extension to both ends of a selected first key component. In each extension cycle, one new component which best meets the current line's shape and style constraints is appended to the line. Different line classes are detected by controlling the line attribute values. As we show in the experiments, the algorithm demonstrates high performance on clear synthetic drawings as well as on noisy, complex, real-world drawings.

Pattern Recognition, 1985

2007

Conceptualization stage in designing engineering product is a process of translating engineer's idea onto a sheet of paper. The product is always sketched on a sheet of paper using pencil. The sketch is tidied up by adding accurate dimension, and complete view of hidden part. This paper discusses part of the process involved in translating the sketch or irregular line drawing into a tidy or regular line drawing, that yield three important entities namely junction, line and region. The chain code algorithm is used to find these entities. The paper also explains explicit thinning process involved before the chain code methodology. Assumptions, important definitions and method of loading image file are also presented. The paper is concluded with several test input sketches, conclusion and future works.

Image and Vision Computing, 1988

1990

Abstract A system for interpretation of images of paper-based line drawings is described. Since a typical drawing contains both text strings and graphics, an algorithm has been developed to locate and separate text strings of various font sizes, styles, and orientations. This is accomplished by applying the Hough transform to the centroids of connected components in the image. The graphics in the segmented image are processed to represent thin entities by their core-lines and thick objects by their boundaries.

1990

An overview is presented of algorithms and techniques for document image analysis with an emphasis on those for grnphics recognition and interpretation. The techniques are derived from the fields of image processing. pattern recognition, and machine vision. The objective in document image analysis is to recognize page contents including layout, text, and figures. Although optical character recognition (OCR) f d s within the context of document image analysis. we do not cover this area. since OCR techniques have been covered extensively in the literature. We also limit the focus to images containing binary information. Topics covered are segmentation of document image into text and graphics regions, vectorization to obtain lines, identification of graphical primitives, and generation of succinct image interpretations.