http://drr.vau.ac.lk/handle/123456789/239 Sun, 05 Apr 2026 19:38:04 GMT 2026-04-05T19:38:04Z http://drr.vau.ac.lk/handle/123456789/371 OFF-LINE HANDWRITTEN SIGNATURE VERIFICATION Praveena, T.; Kokul, T. Off-line handwritten signature is broadly used for personal identification in financial, commercial and legal document bindings. The automatic verification of human handwritten signature is a key research area with respect to improve the verification of forged signature and to reduce the crimes. The objective of this research is to provide a fast, reliable, and easy method to verify off-line handwritten signatures. Image processing techniques and Artificial Neural Network (ANN) are used in this research to achieve a better performance. This research is evaluated on a benchmark dataset, which contains 24 people’s signatures. Five genuine and five forged signature samples of an individual were obtained from the dataset. In the proposed approach, for each person, six signature samples (three genuine signatures and three forged signatures) were used for training and four signature samples (two genuine signatures and two forged signatures) were used for testing. The signature images were in different sizes and different colours such as black, grey, and blue. Therefore, a pre-processing technique was applied in the initial stage. Then, the Speed-Up Robust Features (SURF) were used to extract the information of individuals and then an ANN is used for classification. This research was implemented in MATLAB. Experimental results showed that proposed approach achieved 95.42 % accuracy to identify the genuine signature of an individual. Wed, 02 Dec 2020 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/371 2020-12-02T00:00:00Z http://drr.vau.ac.lk/handle/123456789/370 ROAD DEFECT DETECTION USING HOG FEATURES AND SVM Thushari, B.; Kokul, T. Road defect menace is a widely discussed issue in developing countries including Sri Lanka. The roads must be maintained in proper condition and monitored periodically to ensure the road safety and to reduce problems likes delay in transportation, and higher fuel consumption. We have proposed an automated road defect detection system based on computer vision and machine learning techniques. In the initial stage, road defect images and non-defect images are collected and then pre-processed. In the next step, Histogram of Oriented (HOG) is used as the feature descriptor. Then a Supports Vector Machine (SVM) classifier is used to classify the defect images and non-defect images. A hard-negative mining-based technique is used to improve the performance of the classifier. In the testing, a sliding window technique is applied to locate the defects in road images. Proposed approach is evaluated on CRACK500 benchmark dataset. Experimental results show that proposed approach shows excellent performance and higher accuracy to detect the road defects while comparing with existing methods Wed, 02 Dec 2020 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/370 2020-12-02T00:00:00Z http://drr.vau.ac.lk/handle/123456789/369 FAKE SRI LANKAN CURRENCY DETECTION USING IMAGE PROCESSING TECHNIQUES Murali, K.; Kokul, T. Fake currency is a major crime in Sri Lanka. Due to the advances in printing and scanning technology, it is much difficult to identify a fake currency. This research focuses to verify the Sri Lankan currency notes via image processing techniques. In the initial stage of this study, Sri Lankan currency notes are scanned and pre-processed to remove the background and noises. In the next step, the currency notes are binarized and then segmented. We have extracted the security thread, blind recognition lines, and raised print marks features through image processing algorithms. In the evaluation step, the quantity of obtained features and actual features are compared. Based on the comparison results, we have found that number of lines in raised printed in each denomination currency note (500, 1000 and 5000) are same, size of all the circles in the blind recognition feature in each denomination of currency note has approximately same size, and width of the rectangle in security thread in currency note is same but it differs for each denomination. In conclusion, the proposed work is able to identify the Sri Lankan currency notes by comparing the actual features with image processing features Wed, 02 Dec 2020 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/369 2020-12-02T00:00:00Z http://drr.vau.ac.lk/handle/123456789/368 THE EFFECT OF NUTRIENT LOADING ON ZOOPLANKTON COMMUNITY STRUCTURE INTHANDIKULAM RESERVOIR, VAVUNIYA, SRI LANKA Kottage, C.D.; Patrick, A.E.S. Zooplankton are the heterotrophic aquatic organism that being drift by water currents and itact as a strong linkage between primary producers and secondary consumers. Zooplankton community structure (diversity and abundance) has been identified them as simple, accurate and important ecological indicator to assess eutrophication, acidification and pollution. Thandikulam reservoir is a seasonal reservoir with minimal disturbances of pollution and used for agriculture purpose in Vavuniya District. Therefore, this study was carried out to detect the effect of nutrient loading on zooplankton community structure. Plankton sampling was done by using zooplankton net (80 µm) in randomly selected four locations of this reservoir for couple of times per month from July, 2018 to February, 2019. Simultaneously, water samples were collected at each location to determine nutrient concentrations (NO3- and PO43-), dissolved oxygen and water temperature. Hydro-climatic data (monthly total rainfall, air temperature, water level) were obtained from meteorology department. Species identification was done based on standard zooplankton identification guides under high power of microscope. Abundance of zooplankton community was performed using the Sedgwick-Rafter cell under microscope. Zooplankton diversity was determined according to Shannon-Wiener’s diversity index (H’). Pearson correlation coefficient (r) was obtained to identify the correlations between zooplankton community structure and nutrient concentrations. Total of 19 genera with 12 Rotifer species, 2 Cladocera species and 5 Copepod species were observed. During this study period, high nutrient concentrations were recorded in dry season (July-August, 2018). Increase in PO43- concentration, significantly (p = 0.042) decrease the zooplankton diversity and resulted strong negative correlation (r = - 0.805). Although, increasing NO3- concentration seems to be reducing the zooplankton diversity (r = - 0.686), no significant (p = 0.115) relationship was observed. A negative correlation was recorded in overall zooplankton abundance with PO43-(r = - 0.595, p = 0.145) and NO3-(r = - 0.608, p = 0.138) except Cladocera. Conclusively, this study revealed that nutrient concentration is greatly influenced diversity rather than overall abundance of zooplankton. These findings can be used in monitoring the health and water quality of reservoirs using zooplankton community structure as the principal constituent. Wed, 02 Dec 2020 00:00:00 GMT http://drr.vau.ac.lk/handle/123456789/368 2020-12-02T00:00:00Z