Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting
Handwritten keyword spotting (KWS) is of great interest to the document image research community. In this work, we propose a learning-free keyword spotting method following query by example (QBE) setting for handwritten documents. It consists of four key processes: pre-processing, vertical zone divi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4648 |
| id |
doaj-c0c359a8cfca4db281f600272d4aae67 |
|---|---|
| record_format |
Article |
| spelling |
doaj-c0c359a8cfca4db281f600272d4aae672021-07-23T14:05:09ZengMDPI AGSensors1424-82202021-07-01214648464810.3390/s21144648Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword SpottingSubhranil Kundu0Samir Malakar1Zong Woo Geem2Yoon Young Moon3Pawan Kumar Singh4Ram Sarkar5Department of Electronics and Communication Engineering, National Institute of Technology Durgapur, Durgapur 713209, IndiaDepartment of Computer Science, Asutosh College, Kolkata 700026, IndiaCollege of IT Convergence, Gachon University, 1342 Seongnam Daero, Seongnam 13120, KoreaCollege of IT Convergence, Gachon University, 1342 Seongnam Daero, Seongnam 13120, KoreaDepartment of Information Technology, Jadavpur University, Kolkata 700106, IndiaDepartment of Computer Science and Engineering, Jadavpur University, Kolkata 700032, IndiaHandwritten keyword spotting (KWS) is of great interest to the document image research community. In this work, we propose a learning-free keyword spotting method following query by example (QBE) setting for handwritten documents. It consists of four key processes: pre-processing, vertical zone division, feature extraction, and feature matching. The pre-processing step deals with the noise found in the word images, and the skewness of the handwritings caused by the varied writing styles of the individuals. Next, the vertical zone division splits the word image into several zones. The number of vertical zones is guided by the number of letters in the query word image. To obtain this information (i.e., number of letters in a query word image) during experimentation, we use the text encoding of the query word image. The user provides the information to the system. The feature extraction process involves the use of the Hough transform. The last step is feature matching, which first compares the features extracted from the word images and then generates a similarity score. The performance of this algorithm has been tested on three publicly available datasets: IAM, QUWI, and ICDAR KWS 2015. It is noticed that the proposed method outperforms state-of-the-art learning-free KWS methods considered here for comparison while evaluated on the present datasets. We also evaluate the performance of the present KWS model using state-of-the-art deep features and it is found that the features used in the present work perform better than the deep features extracted using InceptionV3, VGG19, and DenseNet121 models.https://www.mdpi.com/1424-8220/21/14/4648dynamic time warpinghandwritten wordHough transformkeyword spottingquery by example |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Subhranil Kundu Samir Malakar Zong Woo Geem Yoon Young Moon Pawan Kumar Singh Ram Sarkar |
| spellingShingle |
Subhranil Kundu Samir Malakar Zong Woo Geem Yoon Young Moon Pawan Kumar Singh Ram Sarkar Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting Sensors dynamic time warping handwritten word Hough transform keyword spotting query by example |
| author_facet |
Subhranil Kundu Samir Malakar Zong Woo Geem Yoon Young Moon Pawan Kumar Singh Ram Sarkar |
| author_sort |
Subhranil Kundu |
| title |
Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting |
| title_short |
Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting |
| title_full |
Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting |
| title_fullStr |
Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting |
| title_full_unstemmed |
Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting |
| title_sort |
hough transform-based angular features for learning-free handwritten keyword spotting |
| publisher |
MDPI AG |
| series |
Sensors |
| issn |
1424-8220 |
| publishDate |
2021-07-01 |
| description |
Handwritten keyword spotting (KWS) is of great interest to the document image research community. In this work, we propose a learning-free keyword spotting method following query by example (QBE) setting for handwritten documents. It consists of four key processes: pre-processing, vertical zone division, feature extraction, and feature matching. The pre-processing step deals with the noise found in the word images, and the skewness of the handwritings caused by the varied writing styles of the individuals. Next, the vertical zone division splits the word image into several zones. The number of vertical zones is guided by the number of letters in the query word image. To obtain this information (i.e., number of letters in a query word image) during experimentation, we use the text encoding of the query word image. The user provides the information to the system. The feature extraction process involves the use of the Hough transform. The last step is feature matching, which first compares the features extracted from the word images and then generates a similarity score. The performance of this algorithm has been tested on three publicly available datasets: IAM, QUWI, and ICDAR KWS 2015. It is noticed that the proposed method outperforms state-of-the-art learning-free KWS methods considered here for comparison while evaluated on the present datasets. We also evaluate the performance of the present KWS model using state-of-the-art deep features and it is found that the features used in the present work perform better than the deep features extracted using InceptionV3, VGG19, and DenseNet121 models. |
| topic |
dynamic time warping handwritten word Hough transform keyword spotting query by example |
| url |
https://www.mdpi.com/1424-8220/21/14/4648 |
| work_keys_str_mv |
AT subhranilkundu houghtransformbasedangularfeaturesforlearningfreehandwrittenkeywordspotting AT samirmalakar houghtransformbasedangularfeaturesforlearningfreehandwrittenkeywordspotting AT zongwoogeem houghtransformbasedangularfeaturesforlearningfreehandwrittenkeywordspotting AT yoonyoungmoon houghtransformbasedangularfeaturesforlearningfreehandwrittenkeywordspotting AT pawankumarsingh houghtransformbasedangularfeaturesforlearningfreehandwrittenkeywordspotting AT ramsarkar houghtransformbasedangularfeaturesforlearningfreehandwrittenkeywordspotting |
| _version_ |
1721286023450722304 |