Region-based Shape Descriptor Research Articles

Revealing leaf species through specific contour and region-based features extraction

Leaf identification plays a vital role in plant classification and protection, and advancements in artificial intelligence and machine vision have revolutionized leaf identification technology. This study focuses on evaluating different feature extraction methods, specifically region-based and contour-based approaches, to identify plant leaf species through image analysis. The study initially extracts leaf characteristics from images, which are then divided into two groups based on area features or contour features. The dataset is split into 80% for training and 20% for testing, and a K-Nearest Neighbour (K-NN) classifier is employed for species identification. Three approaches are compared for leaf classification. The first approach utilizes region-based shape descriptors (RBSD) and achieves an accuracy rate of 75%. The second approach employs contour-based shape descriptors (CBSD) and achieves a higher accuracy of 76%. The third approach combines both area and contour features, resulting in an average accuracy of 75.5%. Through the comparison of all three methods, it is evident that the CBSD approach outperforms the others, making it the most effective feature extraction method for plant species identification. The developed automatic leaf species identification system was implemented using the PyCharm environment.The proposed approach and feature extraction techniques surpass previous state-of-the-art 69.61%, 72%, 74.4% results, showcasing the potential of the proposed separation of leaf characteristics. Also the advancement of automated leaf species identification and have significant implications for plant taxonomy and protection efforts.

Automatic segmentation method for CFU counting in single plate-serial dilution

Quantification of colony forming units (CFU) on microbial cultures prepared according to the standard spread plate technique is a daily laboratory routine that requires significant resources. On the other hand, SP-SDS (Single Plate Serial Dilution Spotting) is a widely used technique that allows a great reduction in the use of material resources and time. However, previous approaches for automatic quantification are based on images of standard spread plate Petri dishes with low variation of CFU features and captured under controlled lighting conditions. In this paper, we propose a novel approach that automatically separates each dilution in images of Petri dishes prepared in the SP-SDS technique and counts total CFU per dilution, which most approaches are unable to perform. The proposed approach employs region-based shape descriptors for quantification of isolated CFU and cross-correlation granulometry for the quantification of CFU in agglomerates. For the experiments, we composed two image datasets and used images from two publicly available datasets. The images from our datasets were acquired under real laboratory ambient conditions and show variation in lighting, background noise, low contrast between bacterial colonies and background, and high variation in CFU features. Overall, the results obtained by our approach in terms of accuracy, precision, and sensitivity were superior to those of two other approaches recently proposed in the literature used for comparison in this study, especially for high-definition images. In addition, our results present greater or similar accuracy to various approaches found in the literature, most of which are not able to count CFU in images obtained from Petri dishes prepared in the SP-SDS technique and low control of ambient conditions. Our composed datasets are publicly available for download as a contribution to further research.

Shape based Image Retrieval Utilising Colour Moments and Enhanced Boundary Object Detection Technique

The need for automatic object recognition and retrieval have increased rapidly in the last decade. In content-based image retrieval (CBIR) visual cues such as colour, texture, and shape are the most prominent features used. Texture features are not considered as a significant discriminator unless it is integrated with colour features. Colour-based image retrieval uses global and/or local features has proved its ability to retrieve images with a high degree of accuracy. In contrast, shape-based retrieval is still suffering from numerous unsolved problems such as precise edge detection, overlapping objects, and high cost of feature extraction. In this paper, global colour features are utilized to discriminate unrelated images. Furthermore, a novel hybrid approach is proposed, consisting of a combination of boundary-based shape descriptor (BBSD) and region-based shape descriptor (RBSD), image retrieval. An enhanced object boundary detection (EBOD) is proposed, which uses canny edge detector to detect shape boundaries, with morphological opening to remove isolated nodes. Subsequently, morphological closing is utilized to solidify objects within the target image to enhance shape-based features representation. Finally, shape features are extracted and Euclidean distance measure with different threshold values to measure the similarity between feature vectors is adopted. Five semantic categories of WANG image database are selected to test the proposed approach. The results of experiments are promising, when compared with most common related approaches.

Improved shape matching and retrieval using robust histograms of spatially distributed points and angular radial transform

In this paper, the problem of shape based image retrieval is addressed by proposing a hybrid shape descriptor. The proposed descriptor conforms to human visual perception along with its low computational complexity. Since global features are related to the holistic characteristics of images, whereas local features describe the finer details within objects of images, in the proposed hybrid descriptor both global and local features of images are used to describe the entire aspects of image shape. For global features extraction, we use angular radial transform, which is also adopted by MPEG-7 as a region based shape descriptor. On the other hand, for local feature extraction, a novel local descriptor is proposed, which is referred to as histograms of spatially distributed points (HSDP). It is based on two components: radial distance and differential coefficient, which are used to build 2D histograms. Global and local features are combined using effective distance measures viz. Min-Max and Bray-Curtis. Their superiority is validated by experimental results. Apart from that, an extensive range of image databases is employed to assess the performance of the proposed hybrid descriptor. These databases represent several characteristics of shape such as partial occlusion, distortion, subject change, gray scale objects, rotated and noise affected objects, unstructured images, trademarks, blurred images, Corel images, etc. The results of wide range of experiments reveal that the fusion of ART and HSDP significantly improves the image retrieval accuracy and provides a robust and invariant solution for effective shape matching.

An Advanced Approach for Extraction of Brain Tumor from Digital MR Images Using Morphology Gradient & ART

In this work, An Advanced Approach has been proposed for the detection and extraction of brain tumor from magnetic resonance images (MRIs). Magnetic resonance images are visualized and examined using the high order of Angular Radial Transform (ART) and morphological gradient. The Angular Radial Transform (ART) is one of the region-based shape descriptors have many desirable properties such as rotation invariance, robustness to noise, and scale changes. This approach is based on the three steps. Before the segmentation process, the pre-processing of the original image is done by median filter to remove the noise. Then, the morphological gradient is computed and added to the filtered image, and the local statistics values obtained from the high order angular radial transform which are used to calculate the appropriate threshold value. After thresholding, the features of 36 ART of high order are used to extract tumor. These features are then used as input to a support vector machine (SVM) to classify images between normal and abnormal. The experimental results show that the proposed approach is successful to analyze the tumor of the image on testing with different MRIs.

Error Analysis in the Computation of Orthogonal Rotation Invariant Moments

Orthogonal rotation invariant moments (ORIMs) are among the best region based shape descriptors. Being orthogonal and complete, they possess minimum information redundancy. The magnitude of moments is invariant to rotation and reflection and with some geometric transformation, they can be made translation and scale invariant. Apart from these characteristics, they are robust to image noise. These characteristics of ORIMs make them suitable for many pattern recognition and image processing applications. Despite these characteristics, the ORIMs suffer from many digitization errors, thus they are incapable of representing subtle details in image, especially at high orders of moments. Among the various errors, the image discretization error, geometric and numerical integration errors are the most prominent ones. This paper investigates the contribution and effects of these errors on the characteristics of ORIMs and performs a comparative analysis of these errors on the accurate computation of the three major ORIMs: Zernike moments (ZMs), Pseudo Zernike moments (PZMs) and orthogonal Fourier-Mellin moments (OFMMs). Detailed experimental analysis reveals some interesting results on the performance of these moments.

An effective image retrieval using the fusion of global and local transforms based features

Retrieval efficiency and accuracy are the important issues in designing content based image retrieval system. Thus, in this paper, we propose an effective descriptor based on angular radial transform (ART) and polar Hough transform (PHT), which is capable of fulfilling the above requirements. ART is used as a region based shape descriptor, which represents the global aspects of an image. PHT is used as a local shape descriptor for detecting linear edges in an edge image. The detected linear edges represent the association among adjacent edge points. The perpendicular distance of each linear edge to the centroid of the edge image is computed to build histograms, which exhibit rotation, scale and translation invariant properties. The combination of both global (ART based) and local (PHT based) features yields improved retrieval accuracy, which is analyzed over various sorts of image databases. An extensive set of experiments witness the superiority of the proposed hybrid system over other major contour based, region based and hybrid approaches.

Biometric feature extraction with biometric specific shape descriptors

Orthogonal moments, namely Legendre and pseudo-Zernike moments, are popular region-based shape descriptors which can be used to represent regions with invariant feature vectors. In this paper we propose that the accuracy of biometric verification can be improved by selecting a shape descriptor after exploring its suitability for the given shape or biometric. Fingerprint and palmprint biometrics are used for the experiment. It was observed that the inherent nature of the Legendre moments makes it more suitable for palmprint images and that of the Zernike moments makes it more suitable for the fingerprint images.

Fast shape description based on a set of moments defined on the unit disc and inspired by three-dimensional spherical harmonics

A fast region-based shape descriptor, the disk harmonic moments descriptor (DHMD), is proposed. The authors propose a mapping of the 3D spherical harmonics transform (SHT) to the unit disc, and formulate a disc harmonic transform (DHT) based on a new set of orthogonal harmonic moments. Before applying the transform DHT, the shape undergoes a preprocessing in order to ensure shift and scaling invariance. The DHMD is compared to three sets of descriptors: one is formed by three SHT-based descriptors and the other two gather some well-known contour-based and region-based descriptors. The authors consider the set B of the MPEG-7-CE-1 database for experimental validation. To benchmark the performance of the compared descriptors, precision-recall pair is employed. A computational comparison is also proposed. The DHMD achieves faster and better retrievals and seems to be competitive with the cited descriptors. This improvement should encourage the use of DHMD features in different image retrieval systems that support huge databases.

10.1007/s11493-008-1004-5

This paper reports a novel region-based shape descriptor based on orthogonal Legendre moments. The preprocessing steps for invariance improvement of the proposed Improved Legendre Moment Descriptor (ILMD) are discussed. The performance of the ILMD is compared to the MPEG-7 approved region shape descriptor, angular radial transformation descriptor (ARTD), and the widely used Zernike moment descriptor (ZMD). Set B of the MPEG-7 CE-1 contour database and all the datasets of the MPEG-7 CE-2 region database were used for experimental validation. The average normalized modified retrieval rate (ANMRR) and precision-recall pair were employed for benchmarking the performance of the candidate descriptors. The ILMD has lower ANMRR values than ARTD for most of the datasets, and ARTD has a lower value compared to ZMD. This indicates that overall performance of the ILMD is better than that of ARTD and ZMD. This result is confirmed by the precision-recall test where ILMD was found to have better precision rates for most of the datasets tested. Besides retrieval accuracy, ILMD is more compact than ARTD and ZMD. The descriptor proposed is useful as a generic shape descriptor for content-based image retrieval (CBIR) applications.

Robust Affine Invariant Region-Based Shape Descriptors: The ICA Zernike Moment Shape Descriptor and the Whitening Zernike Moment Shape Descriptor

In this letter, we proposed two new affine invariant region-based shape descriptors, the ICA Zernike moment shape descriptor (ICAZMSD) and the whitening Zernike moment shape descriptor (WZMSD). Either independent component analysis (ICA) or whitening, is first used to turn the original shape into a canonical form, in which the effects of scaling and skewing are eliminated. Next, the properties of the Zernike transform are used to further eliminate the effects of any possible rotation and reflection of the canonical shapes, in extracting the Zernike moments as the affine invariant region-based descriptors. Using the proposed ICAZMSD as shape feature, shape-based image retrieval experiments on a 4000 complex shape image database and on a 5600 simple shape image database, show retrieval rates of 99.80% and 92.25%, respectively. Using the proposed WZMSD as shape feature, the corresponding retrieval rates are 99.79% and 92.22%, respectively. The proposed WZMSD has almost equal performance to the proposed ICAZMSD, while having lower computational requirements.

Mode-shape recognition and finite element model updating using the Zernike moment descriptor

In structural finite element model (FEM) updating an important step is the comparison/correlation between the FEM and experimental data. Currently the most widely used method is the modal assurance criterion (MAC), which can be interpreted as the cosine of the angle between numerical (FE model) and measured eigenvectors. However, the eigenvectors only contain the displacement of discrete coordinates, so that the MAC index carries no explicit information on shape features. A new technique, based upon the well-developed philosophies of image processing (IP) and pattern recognition (PR) are considered in this paper. The Zernike moment descriptor (ZMD) is a region-based shape descriptor having outstanding properties in IP including rotational invariance, expression and computing efficiency, ease of reconstruction and robustness to noise. In this paper the ZMD is applied to the problem of mode-shape recognition for simple plate structures. Result shows that the ZMD has considerable advantages over the traditional MAC index when identifying the cyclically symmetric mode shapes that occur in axisymmetric structures at identical frequencies.

An Efficient Technique for the Computation of ART

The angular radial transform (ART) is the region-based shape descriptor for MPEG-7. It is a compact descriptor that presents invariance to simple transformations, while presenting very low information redundancy. However, limited effort has been spent on the fast computation of ART, which is of the essence, especially in systems with sparse computational resources. In this paper, we present an efficient implementation of the descriptor, relating it to accumulation moments. The approximations used are shown not to affect the final 140-bit descriptor, and the architecture is capable of processing images up to one order of magnitude faster than the conventional method.

Performance study of an improved Legendre Moment Descriptor as region-based shape descriptor

This paper reports a novel region-based shape descriptor based on orthogonal Legendre moments. The preprocessing steps for invariance improvement of the proposed Improved Legendre Moment Descriptor (ILMD) are discussed. The performance of the ILMD is compared to the MPEG-7 approved region shape descriptor, angular radial transformation descriptor (ARTD), and the widely used Zernike moment descriptor (ZMD). Set B of the MPEG-7 CE-1 contour database and all the datasets of the MPEG-7 CE-2 region database were used for experimental validation. The average normalized modified retrieval rate (ANMRR) and precision-recall pair were employed for benchmarking the performance of the candidate descriptors. The ILMD has lower ANMRR values than ARTD for most of the datasets, and ARTD has a lower value compared to ZMD. This indicates that overall performance of the ILMD is better than that of ARTD and ZMD. This result is confirmed by the precision-recall test where ILMD was found to have better precision rates for most of the datasets tested. Besides retrieval accuracy, ILMD is more compact than ARTD and ZMD. The descriptor proposed is useful as a generic shape descriptor for content-based image retrieval (CBIR) applications.

Classification of Liver Disease from CT Images Using a Support Vector Machine

We propose a classifier based on the support vector machine (SVM) for automatic classification in liver disease. The SVM, stemming from statistical learning theory, involves state-of-the-art machine learning. The classifier is a part of computer-aided diagnosis (CADx), which assists radiologists in accurately diagnosing liver disease. We formulate discriminating between cysts, hepatoma, cavernous hemangioma, and normal tissue as a supervised learning problem, and apply SVM to classifying the diseases using gray level and co-occurrence matrix features and region-based shape descriptors, calculated from regions of interest (ROIs), as input. Significant features of ROI enable us to simplify SVM input space and to feed the SVM representative information. By simplifying and clarifying the diagnosis process, we separate the classification of liver disease into hierarchical multiclass classification. We use the receiver operating characteristic (ROC) curve to evaluate diagnosis performance, demonstrating the classifier’s good performance.

Fast and efficient method for computing ART

Angular radial transform (ART), which is the region-based shape descriptor of MPEG-7, has desirable properties for representing shape information in a small number of features with no redundancy. However, in order for ART to be useful, especially in limited computing environments, the computational cost of ART must be greatly reduced. In this paper, we derive symmetric/antisymmetric properties from the basis functions of ART and present a fast and efficient method to compute the ART coefficients using these properties. The proposed method significantly reduces the number of sinusoidal operations and multiplications in computing the coefficients of ART. Moreover, the memory requirements needed to store the ART basis functions in lookup tables are only 25% of the conventional method. The experimental results are presented to show the effectiveness of the proposed method.

Generalizations of angular radial transform for 2D and 3D shape retrieval

The angular radial transform (ART) is a moment-based image description method adopted in MPEG-7 as a 2D region-based shape descriptor. This paper proposes generalizations of the ART to describe two-dimensional images and three-dimensional models. First, we propose an 2D extension, called GART, which allows applying ART to images while insuring robustness to all possible rotations and to perspective deformations. Then, we generalize the ART to index 3D models. This new 3D shape descriptor, so called 3D ART, has the same properties that the original transform: robustness to rotation, translation, noise and scaling while keeping a compact size and a good retrieval cost. The size of the descriptor is an essential evaluation parameter on which depends the response time of a content-based retrieval system. For both generalizations, many experiments were made on large databases and have shown, that GART outperforms ART in accuracy at the cost of speed, and that 3D ART outperforms the spherical harmonics shape descriptor (Vranic, D.V., Saupe, D., 2002. Description of 3D-shape using a complex function on the sphere, in: IEEE International Conference on Multimedia and Expo (ICME 2002), Lausanne, Switzerland, 2002, pp. 177–180; Funkhouser, T., Min, P. Kazhdan, M., Chen, J., Halderman, A., Dobkin, D., Jacobs, D., 2003. A search engine for 3D models. ACM Trans. Graphics 22(1), 83–105) in speed at the cost of accuracy.

Evaluation of MPEG-7 shape descriptors against other shape descriptors

Shape is an important image feature-it is one of the primary low level image features exploited in content-based image retrieval (CBIR). There are generally two types of shape descriptors in the literature: contour-based and region-based. In MPEG-7, the curvature scale space descriptor (CSSD) and Zernike moment descriptor (ZMD) have been adopted as the contour-based shape descriptor and region-based shape descriptor, respectively. In this paper, the two shape descriptors are evaluated against other shape descriptors, and the two shape descriptors are also evaluated against each other. Standard methodology is used in the evaluation. Specifically, we use standard databases, large data sets and query sets, commonly used performance measurement and guided principles. A Java-based client-server retrieval framework has been implemented to facilitate the evaluation. Results show that Fourier descriptor (FD) outperforms CSSD, and that CSSD can be replaced by either FD or ZMD.

Shape-based image retrieval using generic Fourier descriptor

Shape description is one of the key parts of image content description for image retrieval . Most of the existing shape descriptors are usually either application dependent or non-robust, making them undesirable for generic shape description. In this paper, a generic Fourier descriptor (GFD) is proposed to overcome the drawbacks of existing shape representation techniques. The proposed shape descriptor is derived by applying two-dimensional Fourier transform on a polar-raster sampled shape image. The acquired shape descriptor is application independent and robust. Experimental results show that the proposed GFD outperforms common contour-based and region-based shape descriptors.

Region-based shape descriptor invariant to rotation, scale and translation

A region-based shape descriptor invariant to rotation, scale and translation is presented in this paper. For a given binary shape, positions of pixels belonging to the shape are regarded as observed vectors of a 2-D random vector and two eigenvectors are obtained from the covariance matrix of the vector population. The shape is divided into four sub-regions by two principal axes corresponding to the two eigenvectors at the center of mass of the shape. Each sub-region is subdivided into four sub-regions in the same way. The sub-division process is repeated for a predetermined number of times. A quadtree representation with its nodes corresponding to regions of the shape is derived from the above process. Four parameters invariant to translation, rotation and scale are calculated for the corresponding region of each node while two parameters are extracted for the root node. The shape descriptor is represented as a vector of all the parameters and the similarity distance between two shapes is calculated by summing up the absolute differences of each element of descriptor vectors. Experimental results conforming to the MPEG-7 shape descriptor core experiments are presented.