Towards more effective distance functions for word image matching

Jain, Raman; Jawahar, C. V.

doi:10.1145/1815330.1815377

Cited by 6 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an alternative to this bottom-up approach, a number of previous works have shown good results for small-vocabulary tasks by performing matching at full-image level, employing global features [4] or feature sequences [21,22] and using a distance-based classification (feasibility for not so small lexicons of 5K words was demonstrated in [24]). These methods are not sensitive to character segmentation and classification, but require at least one image example for every word in the lexicon, which is difficult to collect for large lexicons.…”

Section: Workmentioning

confidence: 99%

Label embedding for text recognition

Rodríguez¹,

Perronnin²

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

The standard approach to recognizing text in images consists in first classifying local image regions into candidate characters and then combining them with high-level word models such as conditional random fields (CRF). This paper explores a new paradigm that departs from this bottom-up view. We propose to embed word labels and word images into a common Euclidean space. Given a word image to be recognized, the text recognition problem is cast as one of retrieval: find the closest word label in this space. This common space is learned using the Structured SVM (SSVM) framework by enforcing matching label-image pairs to be closer than non-matching pairs. This method presents the following advantages: it does not require costly pre-or post-processing operations, it allows for the recognition of never-seen-before words and the recognition process is efficient. Experiments are performed on two challenging datasets (one of license plates and one of scene text) and show that the proposed method is competitive with standard bottom-up approaches to text recognition.

show abstract

Section: Workmentioning

confidence: 99%

Label embedding for text recognition

Rodríguez¹,

Perronnin²

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

show abstract

“…We formulate the retrieval problem in a nearest neighbor setting. In this setting, the distance for finding nearest neighbors can be Euclidean [4] or the cost of alignment of two feature vector sequences with a Dynamic Time Warping (DTW) [5].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Word Image Retrieval in Presence of Font Variations

Ranjan

Harit

Jawahar

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

Abstract-This paper investigates the problem of cross document image retrieval, i.e. use of query images from one style (say font) to perform retrieval from a collection which is in a different style (say a different set of books). We present two approaches to tackle this problem. We propose an effective style independent retrieval scheme using a nonlinear style-content separation model. We also propose a semi-supervised style transfer strategy to expand the query into multiple styles. We validate both these approaches on a collection of word images which vary in fonts/styles.

show abstract

FSOA‐DNFNet: Incremental indexing and image classification using hybrid optimization‐based deep neuro Fuzzy network

Nadendla

Srikrishna

Rao

2022

Concurrency and Computation

View full text Add to dashboard Cite

The rapid evolution and tremendous growth of internet has provided massive growth of unstructured data that leads to a complexity while retrieving dynamic data effectively. The rapid growth in data volume has imposed many challenging constraints, such as necessity to retrieve data completely even if newly arrived samples are occurred and storing of huge volume of data. This has paved a way for concentrating more on incremental learning that functions on information streams. To speed up retrieval, clustering methods and indexes are utilized and periodic updating of clusters is very substantial because of dynamic nature of databases. Moreover, the standard of clustering techniques purely based on data representation techniques, in which traditional methods faced problems like dimensionality explosion and sparsity. To address such limitations, an effectual strategy is developed for incremental indexing and image classification using proposed Feedback Social Optimization Algorithm (FSOA). The image classification is effectively carried out using Deep neuro fuzzy optimizer and it is trained by employing the proposed FSOA and newly FSOA is derived by the integration of Feedback Artificial Tree (FAT) Algorithm and Social Optimization Algorithm (SOA). Moreover, the proposed FSOA has achieved the maximum clustering accuracy of 93.382, the maximum testing accuracy of 94.4, the maximum sensitivity of 91.892, and the maximum specificity of 96.058.

show abstract

Towards more effective distance functions for word image matching

Cited by 6 publications

References 17 publications

Label embedding for text recognition

Label embedding for text recognition

Enhancing Word Image Retrieval in Presence of Font Variations

FSOA‐DNFNet: Incremental indexing and image classification using hybrid optimization‐based deep neuro Fuzzy network

Contact Info

Product

Resources

About