A comparative study using contours and skeletons as shape representations for binary image matching

Chatbri, Houssem; Kameyama, Keisuke; Kwan, Paul

doi:10.1016/j.patrec.2015.04.007

Cited by 11 publications

(9 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Research on shape matching has led to a large repository of shape descriptors that can be classified into methods using global and local features [57], graph-based methods [28], contour-based methods and skeleton based methods [13], in addition to methods using salient keypoints [5,32,35,40].…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, graph matching requires intensive computations and thus it is common to transform a graph into a numerical feature vector in order to speed up computations, which is done at the expense of some information loss [16,27] Contours and skeletons have been used as an intermediate representation before feature extraction. Contours are more robust against noise than skeletons, as skeletons tend to generate noisy branches and artifacts in presence of shape border perturbations [13]. On the other hand, skeletons are more suitable in applications that require the segmentation of the original object into its constituent parts for subsequent graph-based feature representation [3,24,44,51].…”

Section: Related Workmentioning

confidence: 99%

“…Contour detection is used to produce a compact representation of the original image that reduces the number of foreground pixels but preserves the visual information [13,55].…”

Section: Keypoint Extractionmentioning

confidence: 99%

“…Numerous methods have been presented for shape feature extraction in binary images [54,57]. Usually, images are subjected to contour detection or skeletonization before feature extraction in order to remove redundant information and reduce processing time [13].…”

Section: U N C O R R E C T E D P R O O F 1 Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A novel shape descriptor based on salient keypoints detection for binary image matching and retrieval

Chatbri

Kameyama

Kwan

et al. 2018

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

We introduce a shape descriptor that extracts keypoints from binary images and automatically detects the salient ones among them. The proposed descriptor operates as follows: First, the contours of the image are detected and an image transformation is used to generate background information. Next, pixels of the transformed image that have specific characteristics in their local areas are used to extract keypoints. Afterwards, the most salient keypoints are automatically detected by filtering out redundant and sensitive ones. Finally, a feature vector is calculated for each keypoint by using the distribution of contour points in its local area. The proposed descriptor is evaluated using public datasets of silhouette images, handwritten math expressions, hand-drawn diagram sketches, and noisy scanned logos. Experimental results show that the proposed descriptor compares strongly against state of the art methods, and that it is reliable when applied on challenging images such as fluctuated handwriting and noisy scanned images. Furthermore, we integrate our descriptor in a content-based document image retrieval system using sketch queries as a step for query and candidate occurrence matching, and we show that it leads to a significant boost in retrieval performances.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Contour detection is used to produce a compact representation of the original image that reduces the number of foreground pixels but preserves the visual information [13,55].…”

Section: Keypoint Extractionmentioning

confidence: 99%

Section: U N C O R R E C T E D P R O O F 1 Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel shape descriptor based on salient keypoints detection for binary image matching and retrieval

Chatbri

Kameyama

Kwan

et al. 2018

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…El análisis de vecindad de píxel se utiliza para la extracción de contorno, donde un píxel se considera un píxel de contorno si tiene al menos un vecino de fondo [9], para poder obtener las coordenadas de estos pixeles que conforman el contorno de la figura se aplicó en algoritmo de búsqueda A*.…”

Section: Algoritmo De Búsqueda A*unclassified

Clasificación de formas por códigos de cadena mediante un algoritmo de búsqueda

Sandoval¹,

Ramírez-Cruz²,

Islas³

et al. 2018

RCS

View full text Add to dashboard Cite

La clasificación de formas es un proceso utilizado en diversas áreas, para realizar una clasificación a partir de la manipulación de contornos de formas es necesario la extracción de ciertas características comunes para ello se utilizan diferentes técnicas, una de estas es el uso de algoritmos de búsqueda los cuales se encargan de buscar un elemento con ciertas propiedades dentro de una estructura de datos. En este trabajo se presenta una clasificación de formas usando el algoritmo de búsqueda A* y cadenas de código de Freeman, el algoritmo de búsqueda A* busca los pixeles que contienen la información que representa el borde de la forma, esta información es procesada para convertirse en códigos de cadena de Freeman que representan eficientemente los bordes de las formas geométricas, estas técnicas son probadas con diversas formas para comparar las cadenas obtenidas en cada una de ellas y comprobar que se trata de la misma forma con la que se trabajó inicialmente antes de aplicarle las técnicas propuestas.Palabras clave: algoritmo de búsqueda, códigos de cadena, clasificación.

show abstract

Individual identification of Holstein dairy cows based on detecting and matching feature points in body images

Zhao

Jin

et al. 2019

Biosystems Engineering

View full text Add to dashboard Cite

A comparative study using contours and skeletons as shape representations for binary image matching

Cited by 11 publications

References 45 publications

A novel shape descriptor based on salient keypoints detection for binary image matching and retrieval

A novel shape descriptor based on salient keypoints detection for binary image matching and retrieval

Clasificación de formas por códigos de cadena mediante un algoritmo de búsqueda

Individual identification of Holstein dairy cows based on detecting and matching feature points in body images

Contact Info

Product

Resources

About