Fast Keyword Searching Using 'BoostMap' Based Embedding

Saabni, Raid; Bronstein, Alexander M.

doi:10.1109/icfhr.2012.204

Cited by 9 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To represent a word as a sequence, in these works, authors extract column-based features, i.e., features are extracted from each column of the word images. For example, statistical features, eight different features (e.g., distance first data pixels from and bottom, the sum of pixel intensities, transition count, centroid position, and transition at centroid), and multi-angular feature descriptors are used in the works proposed by Rath and Manmatha [ 22 ], Mondal et al [ 17 , 28 ] and Saabni and Bronstein [ 40 ], respectively. DTW is used to perform sequence matching in [ 22 , 40 ], whereas a flexible sequence matching technique is adopted in [ 28 ].…”

Section: Previous Workmentioning

confidence: 99%

“…For example, statistical features, eight different features (e.g., distance first data pixels from and bottom, the sum of pixel intensities, transition count, centroid position, and transition at centroid), and multi-angular feature descriptors are used in the works proposed by Rath and Manmatha [ 22 ], Mondal et al [ 17 , 28 ] and Saabni and Bronstein [ 40 ], respectively. DTW is used to perform sequence matching in [ 22 , 40 ], whereas a flexible sequence matching technique is adopted in [ 28 ]. In another work, Kovalchuk et al [ 41 ] extract histogram of oriented gradients (HOG) and local binary pattern (LBP) feature descriptors from word images segmented into a fixed number of vertical fragments.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting

Kundu

Malakar²,

Geem

et al. 2021

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting

Kundu

Malakar²,

Geem

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…(10), V= {v11,v12,,..v1k,v21,v22,..v2k,...vm1,vm3,..vmk} (10) Here in the Eqs. (9) and (10) where k is the dimension of the feature vector per frame thereby it increases the speed up time in the search operation in the long utterance.…”

Section: Modified Dtw Algorithmmentioning

confidence: 99%

“…Further Fast DTW [10][11][12] method implements DTW in O(N) computations instead of O(N 2 ) computations. To speed up DTW, Sakoe-Chiba band and Itakura parallelogram constraints are analyzed along with a variant of DTW known as Segmental DTW(SDTW) [11].…”

Section: Introductionmentioning

confidence: 99%

Modified Multivariate Euclidean Dynamic Time Warping Based Spoken Keyword Detection

Alex¹,

Nithya²

2017

IJIES

View full text Add to dashboard Cite

Traditional Dynamic Time Warping (DTW) technique find similarities between two one-dimensional time series sequence. Initially, in earlier decades, DTW was not preferred because of its computational complexity. However, due to the evolution of computing power, this has been revisited for spoken keyword detection recently. Conventional spectral features such as Mel-Frequency Cepstral Coefficients (MFCC) and contemporary wavelet features are multi-dimensional in nature which are used in speech recognition. In this work, a new strategy of DTW is proposed to work with multi-dimensional feature vector in calculating the local distance matrix. Additionally, a faster approach is specified to find the similarity in the global distance matrix. The proposed methods are evaluated with MFCC and wavelet features on a connected TIDIGITS corpus for spoken keyword detection system. Experimental results prove that there is an improvement in reduction of computational complexity compared to traditional DTW. Also, contemporary wavelet feature based spoken keyword detection system gave better detection accuracy than MFCC based spoken keyword detection system in the noisy environment.

show abstract

“…There are some method can be used to index biological sequence, such as suffix tree [7][8], suffix array [9], Q-gram [10], Q-samples [9][10], and so on. Different method has different time-complexity and space-complexity.…”

Section: Introductionmentioning

confidence: 99%