Primitive Extraction Research Articles

Syntactic recognition of distorted patterns by means of random graph parsing

In syntactic pattern recognition a pattern can be represented by a graph. Given an unknown pattern represented by a graph g, the problem of recognition is to determine if the graph g belongs to a language L( G) generated by a graph grammar G. The so-called IE graphs have been defined in [Flasiński, M., 1993. On the parsing of deterministic graph languages for syntactic pattern recognition. Pattern Recognition 26, 1–16] for a description of patterns. The IE graphs are generated by so-called ETPL( k) graph grammars defined in (Flasiński, 1993). In practice, structural descriptions may contain pattern distortions. For example, because of errors in the primitive extraction process, an IE graph g representing a pattern under study may be distorted, either in primitive properties or in their relations, so that the assignment of the analysed graph g to a graph language L( G) generated by an ETPL( k) graph grammar G is rejected by the ETPL( k) type parsing (Flasiński, 1993). Therefore, there is a need for constructing effective parsing algorithms for recognition of distorted patterns, represented by graphs, which is the motivation to do research. The purpose of this paper is to present an idea of a new approach to syntactic recognition of distorted patterns represented by so-called random IE graphs.

Automatic Building Extraction from LIDAR Data and Digital Maps

As the use of building models are rapidly increased for various applications, many studies have been performed to develop a practical and nearly automatic method to extract such models from various sensory and GIS data. Nevertheless, it is still a difficult problem to extract the models of large-complex buildings in particular. The purpose of this study is thus to develop a fully automatic method to extract the detail models of buildings from LIDAR data and a digital map. This extraction consisting of primitive extraction and modeling is mainly based on robust segmentation of planar patches from numerous LIDAR points. These primary primitives are used as the references to generate secondary primitives such as edges and corners and then refined based on these secondary primitives to form a complete polyhedral model. The proposed method was successfully applied to extracting large-complex buildings from real data in the test site. It can be a promising time- and cost-effective solution for a country to enhance their traditional map to include 3D models of buildings.

Compound image compression for real-time computer screen image transmission

We present a compound image compression algorithm for real-time applications of computer screen image transmission. It is called shape primitive extraction and coding (SPEC). Real-time image transmission requires that the compression algorithm should not only achieve high compression ratio, but also have low complexity and provide excellent visual quality. SPEC first segments a compound image into text/graphics pixels and pictorial pixels, and then compresses the text/graphics pixels with a new lossless coding algorithm and the pictorial pixels with the standard lossy JPEG, respectively. The segmentation first classifies image blocks into picture and text/graphics blocks by thresholding the number of colors of each block, then extracts shape primitives of text/graphics from picture blocks. Dynamic color palette that tracks recent text/graphics colors is used to separate small shape primitives of text/graphics from pictorial pixels. Shape primitives are also extracted from text/graphics blocks. All shape primitives from both block types are losslessly compressed by using a combined shape-based and palette-based coding algorithm. Then, the losslessly coded bitstream is fed into a LZW coder. Experimental results show that the SPEC has very low complexity and provides visually lossless quality while keeping competitive compression ratios.

An estimation-based approach for range image segmentation: on the reliability of primitive extraction

This paper presents a new algorithm for estimation-based range image segmentation. Aiming at surface-primitive extraction from range data, we focus on the reliability of the primitive representation in the process of region estimation. We introduce an optimal description of surface primitives, by which the uncertainty of a region estimate is explicitly represented with a covariance matrix. Then the reliability of an estimate is interpreted in terms of “measure of uncertainty”. The segmentation approach follows the region-growing scheme, in which the regions are estimated in an iterative way. With the probabilistic model proposed in this paper, surface homogeneity is defined and tested by an optimal criterion. A notable feature of the algorithm is that the order of merging is organized to lead the growth towards the most reliable representation of the merged region. Concerned with man-made objects in the scene, we restrict the class of surface primitives to be quadric or planar. The proposed algorithm has been applied to real data and synthetic data and demonstrated with experimental results.

Straight-line-based primitive extraction in grey-scale object recognition

A method for extraction of straight-line-based primitives is proposed. It is based on a bottom-up approach that extracts linear primitives first, then line segments, that are grouped in straight lines. Based on the extracted lines, quadrangles are detected and further approximated by rectangles. The extracted primitives are used in object recognition. The proposed approach provides a good relation between the complexity of extracted primitives and the complexity of algorithm itself, that allows it to be used in industrial applications.

Classification of Nasal Inspiratory Flow Shapes by Attributed Finite Automata

In a significant proportion of individuals, the physiologic decrease of muscle tone during sleep results in increased collapsibility of the upper respiratory airway. At peak inspiratory flow, the pharyngeal soft tissues may collapse and cause airflow limitation or even complete occlusion of the upper airway (sleep apnea). While there are plenty of methods to detect sleep apnea, only a few can be used to monitor flow limitation in sleeping individuals. Nasal prongs connected to pressure sensor provide information of the nasal airflow over time. This paper documents a method to automatically classify each nasal inspiratory pressure profile into one without flow limitation or six flow-limited ones. The recognition of the sample signals consists of three phases: preprocessing, primitive extraction, and word parsing phases. In the last one, a sequence of signal primitives is treated as a word and we test its membership in the attribute grammars constructed to the signal categories. The method gave in practical tests surprisingly high performance. Classifying 94;pc of the inspiratory profiles in agreement with the visual judgment of an expert physician, the performance of the method was considered good enough to warrant further testing in well-defined patient populations to determine the pressure profile distributions of different subject classes.

Geometric primitive extraction by the combination of tabu search and subpixel accuracy

In this paper, a novel method for extracting the geometric primitives from geometric data is proposed. Specifically, tabu search is combined with subpixel accuracy to improve detection accuracy and convergent speed. On the one hand, this new shape detection method not only has TS's ability to find the global optimum, but also keeps all advantages of tabu search. On the other hand, it has subpixel accuracy ability to match the local optimum.

Structural primitive extraction and coding for handwritten numeral recognition

A structural method is proposed for unconstrained handwritten numeral recognition in this paper. The numeral is first smoothed and the skeleton is obtained. A set of feature points are then detected, and the skeleton is decomposed into primitives. A primitive code is defined to record the information of each primitive, and a global code is derived from the primitive codes to describe the topological structure of the skeleton. According to the global codes, all the numerals are classified into 26 subclasses. Two recognition algorithms have been developed based on the primitive codes. In the first algorithm, prototypes and matching rules are designed by hand. This allows a highly abstract matching rule being designed explicitly. Associated with each recognized numeral, a confidence level is also computed. In the second recognition algorithm, neural networks are used for each subclass, where the learning process can be carried out automatically. Good recognition results have been obtained with digit samples extracted from the NIST database. The performance of the recognition algorithms can still be improved if a more advanced thinning algorithm is used.

Detection of object wings in fused range and intensity imagery

We present methods for detecting primitives in scenes containing objects whose surfaces are approximately piecewise quadric using a sensor that yields fused range and intensity. The primitives detected in a fused image are viewpoint dependent and are called object wings, which consist of adjacent fragments of object contour and surface. Wings are small enough so that some object parts can be sensed despite significant occlusion, yet rich enough to be of use in indexing to candidate models, in constraining object pose, and in aggregation methods which combine primitives into larger structures or objects. Fitting procedures are defined for specific wing primitives. Experiments with both synthetic and real data show that classification within the wing types of planar, spherical, conical, cylindrical can be achieved with over 90% accuracy. Contour information available in fitting fused data improves fitting relative to use of surface data alone. Moreover, it is shown that only a small number of contour and surface samples are needed for extraction of primitives. Oc 1997 Pattern Recognition Society.

Efficient extraction of primitives from line drawings composed of horizontal and vertical lines

The performance of the algorithms for the extraction of primitives for the interpretation of line drawings is usually affected by the degradation of the information contained in the document due to factors such as low print contrast, defocusing, skew, etc. In this paper, we are proposing two algorithms for the extraction of primitives with good performance under degradation. The application of the algorithms is restricted to line drawings composed of horizontal and vertical lines. The performance of the algorithms has been evaluated by using a protocol described in the literature.

A tabu search method for geometric primitive extraction

In this paper, we propose a novel method for extracting the geometric primitives from geometric data, which is essentially an optimization problem. Specifically, we use tabu search to solve geometric primitive extraction problem. To the best of our knowledge, it is the first attempt that tabu search is used in computer vision. Our tabu search (TS) has a number of advantages: (1) TS avoids entrapment in local minima and continues the search to give a near-optimal final solution; (2) TS is very general and conceptually much simpler than either simulated annealing (SA) or genetic algorithm (GA); (3) TS has no special space requirement and is very easy to implement (the entire procedure only occupies a few lines of code); (4) our TS-based method can successfully extract some geometric primitives which are specially difficult for the traditional methods such as Hough Transform (HT) and Robust Statistics (RS). TS is a flexible framework of a variety of strategies originating from artificial intelligence and is therefore open to further improvement.

Fuzzy logic in computer-aided breast cancer diagnosis: analysis of lobulation

This paper illustrates how a fuzzy logic approach can be used to formalize terms in the American College of Radiology (ACR) Breast Imaging Lexicon. In current practice, radiologists make a relatively subjective determination for many terms from the lexicon related to breast cancer diagnosis. Lobulation and microlobulation of nodules are two important features in the ACR lexicon. We offer an approach for formalizing the distinction of these features and also formalize the description of intermediate cases between lobulated and microlobulated masses. In this paper it is shown that fuzzy logic can be an effective tool in dealing with this kind of problem. The proposed formalization creates a basis for the next three steps: (i) extended verification with blinded comparison studies, (ii) the automatic extraction of the related primitives from the image, and (iii) the detection of lobulated and microlobulated masses based on these primitives.

Constructive Fitting and Extraction of Geometric Primitives

We propose a constructive method for fitting and extracting geometric primitives. This method formalizes the merging process of geometric primitives, which is often used in computer vision. Constructive fitting starts from small uniform fits of the data, which are called elemental fits, and uses them to construct larger uniform fits. We present formal results that involve the calculation of the fitting cost, the way in which the elemental fits must be selected, and the way in which they must be combined to construct a large fit. The rules used to combine the elemental fits are very similar to the engineering principles used when building rigid mechanical constructions with rods and joins. In fact, we will characterize the quality of a large fit by a rigidity parameter. Because of its bottom-up approach constructive fitting is particularly well suited for the extraction of geometric primitives when there is a need for a flexible system. To illustrate the main aspects of constructive fitting we discuss the following applications: exact Least Median of Squares fitting, linear regression with a minimal number of elemental fits, the design of a flatness estimator to compute the local flatness of an image, the decomposition of a digital arc into digital straight line segments, and the merging of circle segments.

Primitive coding of structural ECG features

In this paper, a hybrid of self-organizing feature map and learning vector quantization and a rule base classification for the extraction of structural primitives of ECG signals is presented. Structural primitives are the elementary building blocks of an ECG signal and they are used in the syntactic recognition and analysis of the signal. The analysis based on the coding by the codebook vectors and slope rules was as successful as the analysis of the manually labelled test set.

Qualitative primitive identification using fuzzy clustering and invariant approach

This paper addresses the issue of qualitative primitive extraction from range images. The fuzzy C-shell clustering technique is applied to partition range images into a set of quadric shells. Once the best-fitting quadric shells have been recovered, five types of invariants are used to classify the qualitative shapes and represent the geometric parameters of the shapes. Finally, the extracted quadric shells are localised in terms of quadric centre(s), quadric directions, and any axes of revolution. Using fuzzy shell clustering, the shell features can be segmented and fitted simultaneously, and individual best-fitted shells can be clustered concurrently. The integration of the partition with the invariant analysis makes it possible to identify qualitative features from depth maps.

Geometric primitive extraction using a genetic algorithm

Extracting geometric primitives from geometric sensor data is an important problem in model-based vision. A minimal subset is the smallest number of points necessary to define a unique instance of a geometric primitive. A genetic algorithm based on a minimal subset representation is used to perform primitive extraction. It is shown that the genetic approach is an improvement over random search and is capable of extracting more complex primitives than the Hough transform.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Extracting Geometric Primitives

Extracting geometric primitives is an important task in model-based computer vision. The Hough transform is the most common method of extracting geometric primitives. Recently, methods derived from the field of robust statistics have been used for this purpose. We show that extracting a single geometric primitive is equivalent to finding the optimum value of a cost function which has potentially many local minima. Besides providing a unifying way of understanding different primitive extraction algorithms, this model also shows that for efficient extraction the true global minimum must be found with as few evaluations of the cost function as possible. In order to extract a single geometric primitive we choose a number of minimal subsets randomly from the geometric data. The cost function is evaluated for each of these, and the primitive defined by the subset with the best value of the cost function is extracted from the geometric data. To extract multiple primitives, this process is repeated on the geometric data that do not belong to the primitive. The resulting extraction algorithm can be used with a wide variety of geometric primitives and geometric data. It is easily parallelized, and we describe some possible implementations on a variety of parallel architectures. We make a detailed comparison with the Hough transform and show that it has a number of advantages over this classic technique.

A three-dimensional primitive extraction of long bones obtained from bi-dimensional Fourier descriptors

We propose a method for a 3D primitive extraction of long bones using a set of 2D Fourier descriptors. This set is shown to be stable, complete and endowed with geometrical invariancy properties. A polar diagram representation allowing a segmentation of 3D primitives is deduced. The method is illustrated in the case of ulna and radius bones.

Character recognition based on attribute-dependent programmed grammar

The recognition of Korean characters by a syntactic method is considered. Korean characters are composed of phonetic symbols in two dimensions and contain very little redundancy. In addition, the phonetic symbols in each character are different in shape and number depending on how they are composed. Thus, attribute information is important. A Korean character recognition algorithm based on an attribute-dependent programmed grammar is presented. The preprocessing and primitive extraction algorithm is also described. The algorithm was implemented and tested with more than 9600 Korean characters in pages randomly selected from children's story books. The algorithm based on the attribute-dependent programmed grammar recognized characters reasonably quickly, with more than 95.1% accuracy.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Pattern recognition techniques in analyzing the effect of thiourea on brain neurosecretory cells

The effect of thiourea on brain neurosecretory cells has been analysed using pattern recognition and image processing techniques. Preprocessing and primitive extraction are done using fuzzy set theoretic approaches. The syntactic classification of various cellular abnormalities (e.g., normal, initial abnormal, middle abnormal and lethal abnormal), on the other hand, has been achieved using ordinary grammar. An experiment for creating various abnormalities is explained. The pattern variability in terms of dimension is also statistically analysed.