Improving Bangla ocr output through correction algorithms

Bangla OCR (Optical Character Recognition) is a long deserving software for Bengali community all over the world. Numerous e efforts suggest that due to the inherent complex nature of Bangla alphabet and its word formation process development of high fidelity OCR producing a reasonably acceptable output still remains a challenge. One possible way of improvement is by using post processing of OCR’s output; algorithms such as Edit Distance and the use of n-grams statistical information have been used to rectify misspelled words in language processing. This work presents the first known approach to use these algorithms to replace misrecognized words produced by Bangla OCR. The assessment is made on a set of fifty documents written in Bangla script and uses a dictionary of 541,167 words. The proposed correction model can correct several words lowering the recognition error rate by 2.87% and 3.18% for the character based n- gram and edit distance algorithms respectively. The developed system suggests a list of 5 (five) alternatives for a misspelled word. It is found that in 33.82% cases, the correct word is the topmost suggestion of 5 words list for n-gram algorithm while using Edit distance algorithm the first word in the suggestion properly matches 36.31% of the cases. This work will ignite rooms of thoughts for possible improvements in character recognition endeavour.

Identity of a Tilapia Pheromone Released by Dominant Males that Primes Females for Reproduction

Knowledge of the chemical identity and role of urinary pheromones in fish is scarce, yet it is necessary in order to understand the integration of multiple senses in adaptive responses and the evolution of chemical communication [1]. In nature, Mozambique tilapia (Oreochromis mossambicus) males form hierarchies, and females mate preferentially with dominant territorial males, which they visit in aggregations or leks [2]. Dominant males have thicker urinary bladder muscular walls than subordinates or females and store large volumes of urine, which they release at increased frequency in the presence of subordinate males or preovulatory, but not postspawned, females [3–5]. Females exposed to dominant-male urine augment their release of the oocyte maturation-inducing steroid 17α,20β-dihydroxypregn-4-en-3-one (17,20β-P) [6]. Here we isolate and identify a male Mozambique tilapia urinary sex pheromone as two epimeric (20α- and 20β-) pregnanetriol 3-glucuronates. We show that both males and females have high olfactory sensitivity to the two steroids, which cross-adapt upon stimulation. Females exposed to both steroids show a rapid, 10-fold increase in production of 17,20β-P. Thus, the identified urinary steroids prime the female endocrine system to accelerate oocyte maturation and possibly promote spawning synchrony. Tilapia are globally important as a food source but are also invasive species, with devastating impact on local freshwater ecosystems [7, 8]. Identifying the chemical cues that mediate reproduction may lead to the development of tools for population control [9–11].