Phone mismatch penalty matrices for two-stage keyword spotting via multi-pass phone recognizer

Development of a Two-Stage Segmentation-Based Word Searching Method for Handwritten Document Images

Journal of Intelligent Systems ◽

10.1515/jisys-2017-0384 ◽

2018 ◽

Vol 29 (1) ◽

pp. 719-735 ◽

Cited By ~ 2

Author(s):

Samir Malakar ◽

Manosij Ghosh ◽

Ram Sarkar ◽

Mita Nasipuri

Keyword(s):

Feature Vector ◽

Binary Classification ◽

Research Problem ◽

Document Image ◽

Feature Descriptor ◽

Keyword Spotting ◽

Two Stage ◽

Handwritten Documents ◽

And Gender ◽

Searching Method

Abstract Word searching or keyword spotting is an important research problem in the domain of document image processing. The solution to the said problem for handwritten documents is more challenging than for printed ones. In this work, a two-stage word searching schema is introduced. In the first stage, all the irrelevant words with respect to a search word are filtered out from the document page image. This is carried out using a zonal feature vector, called pre-selection feature vector, along with a rule-based binary classification method. In the next step, a holistic word recognition paradigm is used to confirm a pre-selected word as search word. To accomplish this, a modified histogram of oriented gradients-based feature descriptor is combined with a topological feature vector. This method is experimented on a QUWI English database, which is freely available through the International Conference on Document Analysis and Recognition 2015 competition entitled “Writer Identification and Gender Classification.” This technique not only provides good retrieval performance in terms of recall, precision, and F-measure scores, but it also outperforms some state-of-the-art methods.

Download Full-text

Two-stage approach to keyword spotting in handwritten documents

10.1117/12.2042265 ◽

2013 ◽

Author(s):

Mehdi Haji ◽

Mohammad R. Ameri ◽

Tien D. Bui ◽

Ching Y. Suen ◽

Dominique Ponson

Keyword(s):

Keyword Spotting ◽

Two Stage ◽

Handwritten Documents

Download Full-text

Estimation of Phone Mismatch Penalty Matrices for Two-Stage Keyword Spotting

IEICE Transactions on Information and Systems ◽

10.1587/transinf.e93.d.2331 ◽

2010 ◽

Vol E93.D (8) ◽

pp. 2331-2335

Author(s):

Chang Woo HAN ◽

Shin Jae KANG ◽

Nam Soo KIM

Keyword(s):

Keyword Spotting ◽

Two Stage

Download Full-text

Two-stage self-seeding method for preparation of single crystals of poly(phenylene sulfide)

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100153816 ◽

1989 ◽

Vol 47 ◽

pp. 368-369

Author(s):

Sengshiu Chung ◽

Peggy Cebe

Keyword(s):

Single Crystals ◽

High Performance ◽

Dilute Solution ◽

Two Stage ◽

Annealing Behavior ◽

High Performance Polymers ◽

Seeding Method ◽

Phenylene Sulfide

We are studying the crystallization and annealing behavior of high performance polymers, like poly(p-pheny1ene sulfide) PPS, and poly-(etheretherketone), PEEK. Our purpose is to determine whether PPS, which is similar in many ways to PEEK, undergoes reorganization during annealing. In an effort to address the issue of reorganization, we are studying solution grown single crystals of PPS as model materials.Observation of solution grown PPS crystals has been reported. Even from dilute solution, embrionic spherulites and aggregates were formed. We observe that these morphologies result when solutions containing uncrystallized polymer are cooled. To obtain samples of uniform single crystals, we have used two-stage self seeding and solution replacement techniques.

Download Full-text