Abstract
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.
Similar content being viewed by others
References
Abbasi S, Mokhtarian F, Kittler J (1999) Curvature scale space image in shape similarity retrieval. Multimed Syst 7(6):467–476
Baeza-Yates R, Ribeiro-Neto B (1999) Modern information retrieval, vol 463. ACM Press, New York
Bai X, Latecki LJ (2008) Path similarity skeleton graph matching. IEEE Trans Pattern Anal Mach Intell 30(7):1282–1292
Bay H, Tuytelaars T, Van Gool L (2006) Surf: speeded up robust features. In: European conference on computer vision (ECCV), pp 404–417
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522
Bober M (2001) MPEG-7 visual shape descriptors. IEEE Trans Circ Syst Vid Technol 11(6):716–719
Breuß M (2013) Innovations for shape analysis: models and algorithms. Springer Science & Business Media
Bunke H, Riesen K (2012) Towards the unification of structural and statistical pattern recognition. Pattern Recogn Lett 33(7):811–825
Cao T-T, Tang K, Mohamed A, Tan T-S (2010) Parallel banding algorithm to compute exact distance transform with the gpu. In: ACM SIGGRAPH Symposium on interactive 3d graphics and games. ACM, pp 83–90
Chalechale A, Naghdy G, Mertins A (2005) Sketch-based image matching using angular partitioning. In: IEEE Transactions on systems, man and cybernetics, part A: systems and humans
Chatbri H, Kameyama K, Kwan P (2013) Sketch-based image retrieval by size-adaptive and noise-robust feature description. In: International conference on digital image computing: techniques and applications (DICTA). IEEE, pp 1–8
Chatbri H, Davila K, Kameyama K, Zanibbi R (2015) Shape matching using keypoints extracted from both the foreground and the background of binary images. In: International Conference on image processing theory, tools and applications (IPTA). IEEE, pp 205–210
Chatbri H, Kameyama K, Kwan P (2015) A comparative study using contours and skeletons as shape representations for binary image matching. Pattern Recognition Letters
Chatbri H, Kameyama K, Kwan P (2015) Towards a segmentation and recognition-free approach for content-based document image retrieval of handwritten queries. In: Asian Conference on pattern recognition (ACPR). IAPR
da S Torres R, Falcao AX (2007) Contour salience descriptors for effective image retrieval and analysis. Image Vis Comput 25(1):3–13
Demirci FM, van Leuken RH, Veltkamp RC (2008) Indexing through laplacian spectra. Comput Vis Image Underst 110(3):312–325
Donoser M, Riemenschneider H, Bischof H (2010) Efficient partial shape matching of outer contours, 281–292
Dubey SR et al. (2016) Multichannel decoded local binary patterns for content-based image retrieval. IEEE Trans Image Process 25(9):4018–4032
Eitz M, Hays J, Alexa M (2012) How do humans sketch objects? ACM Trans Graph 31(4):44–1
Fernanda AA, Paulo AV, da S Torres MR, Falcão AX (2010) Shape feature extraction and description based on tensor scale. Pattern Recogn 43(1):26–36
Fu J, Wang J, Lu H (2010) Effective logo retrieval with adaptive local feature selection. In: ACM International conference on multimedia (ACM MM). ACM, pp 971–974
Harris C, Stephens M (1988) A combined corner and edge detector. In: Alvey vision conference, pp 147–151
Kopf S, Haenselmann T, Effelsberg W (2005) Enhancing curvature scale space features for robust shape classification. In: International conference on multimedia and expo (ICME). IEEE, p 4–pp
Laiche N, Larabi S, Ladraa F, Khadraoui A (2014) Curve normalization for shape retrieval. Signal Process Image Commun 29(4):556–571
Lee S (2013) Symmetry-driven shape description for image retrieval. Image Vis Comput 31(4):357–363
Liang S, Sun Z (2008) Sketch retrieval and relevance feedback with biased svm classification. Pattern Recogn Lett 29(12):1733–1741
Liang S, Li R-H, Baciu G (2011) A graph modeling and matching method for sketch-based garment panel design. In: International conference on cognitive informatics & cognitive Computing (ICCI CC). IEEE, pp 340–347
Liang S, Luo J, Wenyin L, Wei Y (2015) Sketch matching on topology product graph. IEEE Trans Pattern Anal Mach Intell 37(8):1723–1729
Ling H, Jacobs DW (2007) Shape classification using the inner-distance. IEEE Trans Pattern Anal Mach Intell 29(2):286–299
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis
Meijster A, Roerdink JBTM, Hesselink WH (2000) A general algorithm for computing distance transforms in linear time. In: Mathematical morphology and its applications to image and signal processing. Springer, pp 331–340
Mokhtarian F, Abbasi S, Kittler J (1996) Robust and efficient shape indexing through curvature scale space. In: British machine and vision conference (BMVC), vol 96
Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 11(285-296):23–27
Pedrosa GV, Barcelos CAZ (2010) Anisotropic diffusion for effective shape corner point detection. Pattern Recogn Lett 31(12):1658–1664
Pedrosa GV, Batista MA, Barcelos CAZ (2013) Image feature descriptor based on shape salience points. Neurocomputing
Qi W, Zou C, Yuan Y, Hongbing L, Yan P (2013) Image registration by normalized mapping. Neurocomputing 101:181–189
Qian Y, Yang Y, Song Y-Z, Xiang T, Hospedales T (2015) Sketch-a-net that beats humans arXiv:1501.07873
Ren Z, Yuan J, Meng J, Zhang Z (2013) Robust part-based hand gesture recognition using kinect sensor. IEEE Trans Multimed 15(5):1110–1120
Richards W, Hoffman DD (1985) Codon constraints on closed 2D shapes. Comput Vis Graph Image Process 31(3):265–281
Roman-Rangel E, Marchand-Maillet S (2014) Hoosc128: a more robust local shape descriptor. In: Pattern recognition, volume 8495 of Lecture notes in computer science. Springer, pp 172–181
Roman-Rangel E, Marchand-Maillet S (2015) Shape-based detection of maya hieroglyphs using weighted bag representations. Pattern Recogn 48(4):1161–1173
Rosenfeld A, Pfaltz JL (1966) Sequential operations in digital picture processing. J ACM (JACM) 13(4):471–494
Roy Davies E (2004) Machine vision: theory, algorithms, practicalities. Elsevier
Saha PK, Borgefors G, Sanniti di Baja G (2015) A survey on skeletonization algorithms and their applications. Pattern Recognition Letters
Sebastian T, Klein P, Kimia B (2001) Recognition of shapes by editing shock graphs. In: International conference on computer vision (ICCV), vol 1. IEEE, pp 755–755
Sebe N, Qi T, Loupias E, Lew MS, Huang TS (2003) Evaluation of salient point techniques. Image Vis Comput 21(13):1087–1095
Sezgin TM, Davis R (2007) Scale-space based feature point detection for digital ink. In: ACM SIGGRAPH 2007 courses. ACM, p 36
Shafait F, Keysers D, Breuel TM (2008) Efficient implementation of local adaptive thresholding techniques using integral images. In: Document recognition and retrieval XV
Shu X, Xiao-Jun W (2011) A novel contour descriptor for 2D shape matching and its application to image retrieval. Image Vis Comput 29(4):286–294
Song J, Song Y-Z, Xiang T, Hospedales T, Ruan X (2016) Deep multi-task attribute-driven ranking for fine-grained sketch-based image retrieval. In: British Machine vision conference (BMVC), vol 3
Sundar H, Silver D, Gagvani N, Dickinson S (2003) Skeleton based shape matching and retrieval. In: Shape modeling international. IEEE, pp 130–139
Tyler CW (2002) Human symmetry perception and its computational analysis. Psychology Press
Witkin AP (1984) Scale-space filtering: a new approach to multi-scale description. In: International conference on acoustics, speech, and signal processing (ICASSP), vol 9. IEEE, pp 150–153
Yang M, Kpalma K, Ronsin J (2008) A survey of shape feature extraction techniques. Pattern Recogn, 43–90
Yang X, Liu H, Latecki LJ (2012) Contour-based object detection as dominant set computation. Pattern Recogn 45(5):1927–1936
Zanibbi R, Yu L (2011) Math spotting: retrieving math in technical documents using handwritten query images. In: International Conference on document analysis and recognition (ICDAR)
Zhang D, Guojun L (2004) Review of shape representation and description techniques. Pattern Recogn 37(1):1–19
Zhang D, Lu G (2002) A comparative study of fourier descriptors for shape representation and retrieval. In: Asian Conferernce on computer vision (ACCV), pp 646–651
Zhao Peng, Guoqin W u, Yijuan L u, Xianwen W u, Yao Sheng (2016) A novel hand-drawn sketch descriptor based on the fusion of multiple features. Neurocomputing 213:66–74
Zhu G, Doermann D (2007) Automatic document logo detection. In: International conference on document analysis and recognition (ICDAR), pp 864–868
Zhu F, Xie J, Fang Y (2016) Learning cross-domain neural networks for sketch-based 3d shape retrieval. In: AAAI Conference on artificial intelligence. AAAI Press, pp 3683–3689
Acknowledgments
This work has emanated from a research grant in part from the Monbukagakusho Scholarship sponsored by the Japanese Government, in part from the Irish Research Council (IRC) under Grant Number GOIPD/2016/61, and in part from Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289 (Insight Centre for Data Analytics). The authors would also like to thank Dr. Richard Zanibbi for providing his dataset [56], Dr. Mathieu Delalandre and Dr. Alireza Alaei for their assistance with extracting logos from the Tobacco 800 dataset, and Dr. Shuang Liang for her assistance with her dataset [28].
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chatbri, H., Kameyama, K., Kwan, P. et al. A novel shape descriptor based on salient keypoints detection for binary image matching and retrieval. Multimed Tools Appl 77, 28925–28948 (2018). https://doi.org/10.1007/s11042-018-6054-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6054-x