Symbol Spotting in Offline Handwritten Mathematical Expressions
18 Dec 2018-pp 52-64
TL;DR: A new segmentation-free approach is proposed which matches convex shape portions of symbols occurring in various layout such as subscript, superscript, fraction etc and is able to perform spotting of symbols present in a handwritten expression.
Abstract: Recognition of touching characters in mathematical expressions is a challenging problem in the field of document image analysis. Various approaches for recognizing touching maths symbols have been reported in literature, but they mainly dealt with printed expressions and handwritten numeral strings. In this work, a new segmentation-free approach is proposed which matches convex shape portions of symbols occurring in various layout such as subscript, superscript, fraction etc. and is able to perform spotting of symbols present in a handwritten expression. Our contribution lies in the design of a novel feature which can handle touching symbols effectively in the presence of handwriting variations. This recognition-based approach helps in spotting symbols in an expression even in the presence of clutter created by the presence of other symbols.
Citations
More filters
04 May 2023
TL;DR: In this paper , the SVR algorithm encodes the image, produces a model that fits the data better, and the result is then obtained by character-wise segmenting the image and comparing it with trained models.
Abstract: One of the most important tasks in the realm of document analysis and recognition is the detection of equations in documents that were acquired using a camera. The procedure includes several steps, including pre-processing of the images, segmentation, feature extraction, and classification. The suggested method comprises taking a user-provided input expression image and classifying it into one of three types of equations: simple, complex, and highly complex. By choosing a decision boundary set off from the initial hyperplane, the SVR algorithm encodes the image, producing a model that fits the data better. The result is then obtained by character-wise segmenting the image and comparing it with trained models. Two recurrent neural networks make up the RNN encoder-decoder that is used. One RNN creates a fixed-length vector representation from a sequence of symbols, and a different RNN decodes that representation into a different sequence of symbols. 1900 images containing various equations made up the dataset utilized for training, validating, and testing the SVR and RNN. The accuracy of the system was about 93.64%.
04 May 2023
TL;DR: In this article , the SVR algorithm encodes the image, produces a model that fits the data better, and the result is then obtained by character-wise segmenting the image and comparing it with trained models.
Abstract: One of the most important tasks in the realm of document analysis and recognition is the detection of equations in documents that were acquired using a camera. The procedure includes several steps, including pre-processing of the images, segmentation, feature extraction, and classification. The suggested method comprises taking a user-provided input expression image and classifying it into one of three types of equations: simple, complex, and highly complex. By choosing a decision boundary set off from the initial hyperplane, the SVR algorithm encodes the image, producing a model that fits the data better. The result is then obtained by character-wise segmenting the image and comparing it with trained models. Two recurrent neural networks make up the RNN encoder-decoder that is used. One RNN creates a fixed-length vector representation from a sequence of symbols, and a different RNN decodes that representation into a different sequence of symbols. 1900 images containing various equations made up the dataset utilized for training, validating, and testing the SVR and RNN. The accuracy of the system was about 93.64%.
References
More filters
Proceedings Article•
01 Jan 2000TL;DR: It is demonstrated that shape contexts greatly simplify recovery of correspondences between points of two given shapes, and is used in a nearest-neighbor classifier for recognition of hand written digits as well as 3D objects, using exactly the same distance function.
Abstract: We develop an approach to object recognition based on matching shapes and using a resulting measure of similarity in a nearest neighbor classifier. The key algorithmic problem here is that of finding pointwise correspondences between an image shape and a stored prototype shape. We introduce a new shape descriptor, the shape context, which makes this possible, using a simple and robust algorithm. The shape context at a point captures the distribution over relative positions of other shape points and thus summarizes global shape in a rich, local descriptor. We demonstrate that shape contexts greatly simplify recovery of correspondences between points of two given shapes. Once shapes are aligned, shape contexts are used to define a robust score for measuring shape similarity. We have used this score in a nearest-neighbor classifier for recognition of hand written digits as well as 3D objects, using exactly the same distance function. On the benchmark MNIST dataset of handwritten digits, this yields an error rate of 0.63%, outperforming other published techniques.
611 citations
TL;DR: A robust scheme to take care of variability involved in the writing style of different individuals a robust scheme is presented here, mainly based on features obtained from a concept based on water reservoir.
161 citations
12 Oct 2008
TL;DR: This work introduces a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar, and uses salient contours as integral tokens for shape matching.
Abstract: We introduce a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar. Shape based detection is invariant to changes of object appearance, and can reason with geometrical abstraction of the object. Our approach uses salient contours as integral tokens for shape matching. We seek a maximal, holistic matching of shapes, which checks shape features from a large spatial extent, as well as long-range contextual relationships among object parts. This amounts to finding the correct figure/ground contour labeling, and optimal correspondences between control points on/around contours. This removes accidental alignments and does not hallucinate objects in background clutter, without negative training examples. We formulate this task as a set-to-set contour matching problem. Naive methods would require searching over 'exponentially' many figure/ground contour labelings. We simplify this task by encoding the shape descriptor algebraically in a linear form of contour figure/ground variables. This allows us to use the reliable optimization technique of Linear Programming. We demonstrate our approach on the challenging task of detecting bottles, swans and other objects in cluttered images.
117 citations
TL;DR: Experimental results show that the filter can eliminate up to 83% of the unnecessary segmentation hypothesis and increase the overall performance of the system.
42 citations
03 Aug 2003
TL;DR: Experimental results showed the effectiveness on the accuracy improvement of the recognition of mathematical expressions and the segmentation of touching characters in mathematical expressions.
Abstract: A technique for the detection and the segmentation of touching characters in mathematical expressions is presented. In the detection stage, a connected component initially recognized into some category is judged as a candidate of touched characters if its feature values deviate from the standard feature values of the category. In the segmentation stage, two component characters of the candidate are decided by the comparison with touching character images synthesized from two single character images. Experimental results showed the effectiveness on the accuracy improvement of the recognition of mathematical expressions.
32 citations