Machine vision for keyword spotting using pseudo 2D hidden Markov models

An algorithm for robust machine recognition of keywords embedded in a poorly printed document is presented. For each keyword, two statistical models, called pseudo-2D hidden Markov models (P2-DHMMs), are created for representing the actual keyword and all the other extraneous words, respectively. Dynamic programming is then used for matching an unknown input word with the two models and making a maximum likelihood decision. Although the models are pseudo 2-D in the sense that they are not fully connected 2-D networks, they are shown to be general enough to characterize printed words efficiently. These models facilitate a nice ´elastic matching´ property in both horizontal and vertical directions, which makes the recognizer not only independent of size and slant but also tolerant of highly deformed and noisy words. The system is evaluated on a synthetically created database which contains about 26000 words. A recognition accuracy of 99% is achieved when words in testing and training sets are in the same font size. An accuracy of 96% is achieved when they are in different sizes. In the latter case, the conventional 1-D HMM approach achieves only 70% accuracy rate.<>