The quality of the watermarking technique greatly depends on the selection of the watermark struc... more The quality of the watermarking technique greatly depends on the selection of the watermark structure and insertion strategy. In the problem of watermarking, the involved two main constraints are those of maintaining the robustness of the watermark information while keeping the visual perception of the original image intact. For this purpose, the most important properties are robustness and invisibility. The main objective of the proposed algorithm is to improve the perceptual quality of the watermarked image without violating its robustness against the different attacks. The host image is being divided into four non-overlapping multi-resolution sub-bands by applying Discrete Wavelet Transform (DWT). In the proposed algorithm, horizontal detail region of the host image is being chosen for embedding the watermark. The DWT is also applied to the watermark and its approximation region is chosen to embed into the host image as this region has the most visual perceptual quality for human...
License Plate Recognition (LPR) is a mass superintending system that captures the image of vehicl... more License Plate Recognition (LPR) is a mass superintending system that captures the image of vehicles and recognizes their license number. There has been a little of work done on Bangla license plate detection which is very important for recognizing the Bangla license plate. The plates with different backgrounds make it more complicated to use the existing algorithms. In this paper, we introduce a new algorithm for detecting Bangla license plate. At first, vehicle location is determined. In Bangladesh, Bangla license plates have some of the unique colors like green for the commercial vehicle and white for the personal vehicle. That’s why the portions of green and white colors are selected with the matching RGB intensity of the plate. Then contour algorithm and aspect ratio have been used to locate the license plate region. The rows of the license plate contain registration information that are separated using horizontal projection with the appropriate threshold value. After that, the ...
To understand the cell movement and cell behavior into different parts of organs in human or anim... more To understand the cell movement and cell behavior into different parts of organs in human or animal body, it is necessary to study the cells in culture medium. Fluorescence microscopy is an emerging tool for acquiring this cellular images. The large number of cellular images produced by fluorescence microscopy is unmanageable for human to analyze them manually. Thus, cellular image segmentation is a primary requirement for higher level analysis of medical diagnosis and research. In this paper, a fully automatic method for segmentation of cells from fluorescent microscopy images is proposed. The method first mark the probable foreground and background seeds planted on the image. Then it applies a popular segmentation method, namely watershed segmentation, based on these seeds. The result is further refined based on the gradient value along the initial segmented lines and then again performing watershed transform on the distance transformed image of the previously founded result. The ...
The general algorithms which are followed to solve the Longest Common Subsequence (LCS) problems ... more The general algorithms which are followed to solve the Longest Common Subsequence (LCS) problems have both time complexity and space complexity of O(m * n). To reduce this complexity, two ways are proposed in this work. One is the use of Divide and Conquer approach, and another one is changing the data structure from two-dimensional array to queue. By using these approaches, an algorithm has been developed and implemented for the long length string in this paper. The time complexity after using these approaches becomes a function of logarithm O(n * log(n)) which has been shown with proper explanation and the space complexity after using queue data structure becomes linear O(n).
Detection and tilt correction of vehicle license plates are inevitable problems to be solved befo... more Detection and tilt correction of vehicle license plates are inevitable problems to be solved before developing Intelligent Transportation Systems. This paper describes a method of extraction of the vehicle license plate region from a vehicle image with tilt correction. The method consists of five distinct phases: segmenting color, labeling and filtering, correcting tilt, verifying candidate region, and segmenting license plate characters. Initially, an adaptive technique with labeling and filtering capability is utilized to select a statistical threshold value in the HSI color space for detecting candidate vehicle license plate regions. In this way the proposed method can overcome the limitation of the failure to detect a license plate when the vehicle body and license plate are similar colors. The slopes and tilt angles in both the horizontal and vertical directions of the skewed vehicle license plate are determined using the candidate corner points detected by the Smallest Univalue Segment Assimilating Nucleus corner detector, and the license plate region is rotated accordingly. Finally, a horizontal and vertical position histogram is employed to segment the candidate region into rows and constituent characters. The proposed tilt correction method is compared with the least square fitting with perpendicular offsets method and found to outperform results when the tilt angle gradually increases. 145 vehicle images were used for testing with different conditions and the results are presented to prove its efficiency and effectiveness.
International Journal of Computer Science and Information Technology
Nowadays social media has become one of the largest gatherings of people in online. There are man... more Nowadays social media has become one of the largest gatherings of people in online. There are many ways for the industries to promote their products to the public through advertising. The variety of advertisement is increasing dramatically. Businessmen are so much dependent on the advertisement that significantly it really brought out success in the market and hence practiced by major industries. Thus, companies are trying hard to draw the attention of customers on social networks through online advertisement. One of the most popular social media is Twitter which is popular for short text sharing named 'Tweet'. People here create their profile with basic information. To ensure the advertisements are shown to relative people, Twitter targets people based on language, gender, interest, follower, device, behaviour, tailored audiences, keyword, and geography targeting. Twitter generates interest sets based on their activities on Twitter. What our framework does is that it determines the topic of interest from a given list of Tweets if it has any. This process is called Entity Intersect Categorizing Value (EICV). Each category topic generates a set of words or phrases related to that topic. An entity set is created from processing tweets by keyword generation and Twitters data using Twitter API. Value of entities is matched with the set of categories. If they cross a threshold value, it results in the category which matched the desired interest category. For smaller amounts of data sizes, the results show that our framework performs with higher accuracy rate.
International Journal of Scientific and Research Publications (IJSRP)
Electricity is the key factor for gradual development of any country let alone developing country... more Electricity is the key factor for gradual development of any country let alone developing country like Bangladesh. The demand for electricity in both households and industries is increasing rapidly with the increase of the population in Bangladesh [11]. Currently, load shedding is common phenomenon, which is causing severe problem for the country and, is hindering the progress of economy [6]. There are some key reasons for this ongoing problem such as ever increasing demand for electricity, limited natural resources, lower capacity of electricity generation, and less investment (both private and public) in this sector etc. [1,4]. Electricity crisis needs to be abolished as soon as possible in order to become Bangladesh as a developed country [9]. In this regards, the paper presents a low cost but effective and efficient model (fan with dynamo) for generating electricity which might fulfil the increasing demand in the rural areas, where the electricity from the main grid could not be possible, as well as rest of the country. Firstly, the author discusses the present scenario of electricity production system in Bangladesh and its crisis due to the increasing demand and reduces productivity. Finally, a low cost model for electricity generation to eradicate the gap between demand and supply of electricity is presented.
International Journal of Advanced Science and Technology
The world is digitalizing day by day because of the contribution of science and technology. Intel... more The world is digitalizing day by day because of the contribution of science and technology. Intelligent Transport System (ITS) is a prominent innovation of this technology. It is an outstanding system which contributes not only to the betterment of human lives and environment but also to save time. Road sign recognition is one of the prominent sectors in the ITS. It provides real-time data on traffic for processing to take proper actions. This paper represents a color and shape based road sign detection model. As most of the road signs in Bangladesh are red; so, red channel of the image is extracted for detecting road sign accurately. A robust binarization technique is used to find the largest blob which indicates the region of interest (ROI). To extract ROI, the bounding box is used which is imposed on the RGB image. For decreasing computation time, the grayscale color space is used here. Then the features of the image are extracted and recognized by matching with the images in the database using Speed Up Robust Features (SURF) method. This method provides more accurate results in recognizing road signs. Various road sign images are used with a variety of conditions to test the proposed framework and results are presented to prove its effectiveness.
2010 13th International Conference on Computer and Information Technology (ICCIT), 2010
Abstract Cooperative communication has been considered as a promising method for benefiting the a... more Abstract Cooperative communication has been considered as a promising method for benefiting the advantages from MIMO (multiple-input multiple-output) system for single antenna mobiles in the wireless network, and many important milestones in this area have been achieved, ...
2010 13th International Conference on Computer and Information Technology (ICCIT), 2010
This paper presents a prototype implementation of an intelligent system called safe system that m... more This paper presents a prototype implementation of an intelligent system called safe system that monitors container security in the port logistics. Logistics supports in the port require safe container status. The main focus of our contribution is to design a system that supports RFID (Radio Frequency Identification) Readers of all types (such as Reader Protocol complaint and vendor provided Readers),
Cooperative communication has been considered as a promising method for benefiting the advantages... more Cooperative communication has been considered as a promising method for benefiting the advantages from MIMO (multiple-input multiple-output) system for single antenna mobiles in the wireless network, and many important milestones in this area have been achieved, ...
The quality of the watermarking technique greatly depends on the selection of the watermark struc... more The quality of the watermarking technique greatly depends on the selection of the watermark structure and insertion strategy. In the problem of watermarking, the involved two main constraints are those of maintaining the robustness of the watermark information while keeping the visual perception of the original image intact. For this purpose, the most important properties are robustness and invisibility. The main objective of the proposed algorithm is to improve the perceptual quality of the watermarked image without violating its robustness against the different attacks. The host image is being divided into four non-overlapping multi-resolution sub-bands by applying Discrete Wavelet Transform (DWT). In the proposed algorithm, horizontal detail region of the host image is being chosen for embedding the watermark. The DWT is also applied to the watermark and its approximation region is chosen to embed into the host image as this region has the most visual perceptual quality for human...
License Plate Recognition (LPR) is a mass superintending system that captures the image of vehicl... more License Plate Recognition (LPR) is a mass superintending system that captures the image of vehicles and recognizes their license number. There has been a little of work done on Bangla license plate detection which is very important for recognizing the Bangla license plate. The plates with different backgrounds make it more complicated to use the existing algorithms. In this paper, we introduce a new algorithm for detecting Bangla license plate. At first, vehicle location is determined. In Bangladesh, Bangla license plates have some of the unique colors like green for the commercial vehicle and white for the personal vehicle. That’s why the portions of green and white colors are selected with the matching RGB intensity of the plate. Then contour algorithm and aspect ratio have been used to locate the license plate region. The rows of the license plate contain registration information that are separated using horizontal projection with the appropriate threshold value. After that, the ...
To understand the cell movement and cell behavior into different parts of organs in human or anim... more To understand the cell movement and cell behavior into different parts of organs in human or animal body, it is necessary to study the cells in culture medium. Fluorescence microscopy is an emerging tool for acquiring this cellular images. The large number of cellular images produced by fluorescence microscopy is unmanageable for human to analyze them manually. Thus, cellular image segmentation is a primary requirement for higher level analysis of medical diagnosis and research. In this paper, a fully automatic method for segmentation of cells from fluorescent microscopy images is proposed. The method first mark the probable foreground and background seeds planted on the image. Then it applies a popular segmentation method, namely watershed segmentation, based on these seeds. The result is further refined based on the gradient value along the initial segmented lines and then again performing watershed transform on the distance transformed image of the previously founded result. The ...
The general algorithms which are followed to solve the Longest Common Subsequence (LCS) problems ... more The general algorithms which are followed to solve the Longest Common Subsequence (LCS) problems have both time complexity and space complexity of O(m * n). To reduce this complexity, two ways are proposed in this work. One is the use of Divide and Conquer approach, and another one is changing the data structure from two-dimensional array to queue. By using these approaches, an algorithm has been developed and implemented for the long length string in this paper. The time complexity after using these approaches becomes a function of logarithm O(n * log(n)) which has been shown with proper explanation and the space complexity after using queue data structure becomes linear O(n).
Detection and tilt correction of vehicle license plates are inevitable problems to be solved befo... more Detection and tilt correction of vehicle license plates are inevitable problems to be solved before developing Intelligent Transportation Systems. This paper describes a method of extraction of the vehicle license plate region from a vehicle image with tilt correction. The method consists of five distinct phases: segmenting color, labeling and filtering, correcting tilt, verifying candidate region, and segmenting license plate characters. Initially, an adaptive technique with labeling and filtering capability is utilized to select a statistical threshold value in the HSI color space for detecting candidate vehicle license plate regions. In this way the proposed method can overcome the limitation of the failure to detect a license plate when the vehicle body and license plate are similar colors. The slopes and tilt angles in both the horizontal and vertical directions of the skewed vehicle license plate are determined using the candidate corner points detected by the Smallest Univalue Segment Assimilating Nucleus corner detector, and the license plate region is rotated accordingly. Finally, a horizontal and vertical position histogram is employed to segment the candidate region into rows and constituent characters. The proposed tilt correction method is compared with the least square fitting with perpendicular offsets method and found to outperform results when the tilt angle gradually increases. 145 vehicle images were used for testing with different conditions and the results are presented to prove its efficiency and effectiveness.
International Journal of Computer Science and Information Technology
Nowadays social media has become one of the largest gatherings of people in online. There are man... more Nowadays social media has become one of the largest gatherings of people in online. There are many ways for the industries to promote their products to the public through advertising. The variety of advertisement is increasing dramatically. Businessmen are so much dependent on the advertisement that significantly it really brought out success in the market and hence practiced by major industries. Thus, companies are trying hard to draw the attention of customers on social networks through online advertisement. One of the most popular social media is Twitter which is popular for short text sharing named 'Tweet'. People here create their profile with basic information. To ensure the advertisements are shown to relative people, Twitter targets people based on language, gender, interest, follower, device, behaviour, tailored audiences, keyword, and geography targeting. Twitter generates interest sets based on their activities on Twitter. What our framework does is that it determines the topic of interest from a given list of Tweets if it has any. This process is called Entity Intersect Categorizing Value (EICV). Each category topic generates a set of words or phrases related to that topic. An entity set is created from processing tweets by keyword generation and Twitters data using Twitter API. Value of entities is matched with the set of categories. If they cross a threshold value, it results in the category which matched the desired interest category. For smaller amounts of data sizes, the results show that our framework performs with higher accuracy rate.
International Journal of Scientific and Research Publications (IJSRP)
Electricity is the key factor for gradual development of any country let alone developing country... more Electricity is the key factor for gradual development of any country let alone developing country like Bangladesh. The demand for electricity in both households and industries is increasing rapidly with the increase of the population in Bangladesh [11]. Currently, load shedding is common phenomenon, which is causing severe problem for the country and, is hindering the progress of economy [6]. There are some key reasons for this ongoing problem such as ever increasing demand for electricity, limited natural resources, lower capacity of electricity generation, and less investment (both private and public) in this sector etc. [1,4]. Electricity crisis needs to be abolished as soon as possible in order to become Bangladesh as a developed country [9]. In this regards, the paper presents a low cost but effective and efficient model (fan with dynamo) for generating electricity which might fulfil the increasing demand in the rural areas, where the electricity from the main grid could not be possible, as well as rest of the country. Firstly, the author discusses the present scenario of electricity production system in Bangladesh and its crisis due to the increasing demand and reduces productivity. Finally, a low cost model for electricity generation to eradicate the gap between demand and supply of electricity is presented.
International Journal of Advanced Science and Technology
The world is digitalizing day by day because of the contribution of science and technology. Intel... more The world is digitalizing day by day because of the contribution of science and technology. Intelligent Transport System (ITS) is a prominent innovation of this technology. It is an outstanding system which contributes not only to the betterment of human lives and environment but also to save time. Road sign recognition is one of the prominent sectors in the ITS. It provides real-time data on traffic for processing to take proper actions. This paper represents a color and shape based road sign detection model. As most of the road signs in Bangladesh are red; so, red channel of the image is extracted for detecting road sign accurately. A robust binarization technique is used to find the largest blob which indicates the region of interest (ROI). To extract ROI, the bounding box is used which is imposed on the RGB image. For decreasing computation time, the grayscale color space is used here. Then the features of the image are extracted and recognized by matching with the images in the database using Speed Up Robust Features (SURF) method. This method provides more accurate results in recognizing road signs. Various road sign images are used with a variety of conditions to test the proposed framework and results are presented to prove its effectiveness.
2010 13th International Conference on Computer and Information Technology (ICCIT), 2010
Abstract Cooperative communication has been considered as a promising method for benefiting the a... more Abstract Cooperative communication has been considered as a promising method for benefiting the advantages from MIMO (multiple-input multiple-output) system for single antenna mobiles in the wireless network, and many important milestones in this area have been achieved, ...
2010 13th International Conference on Computer and Information Technology (ICCIT), 2010
This paper presents a prototype implementation of an intelligent system called safe system that m... more This paper presents a prototype implementation of an intelligent system called safe system that monitors container security in the port logistics. Logistics supports in the port require safe container status. The main focus of our contribution is to design a system that supports RFID (Radio Frequency Identification) Readers of all types (such as Reader Protocol complaint and vendor provided Readers),
Cooperative communication has been considered as a promising method for benefiting the advantages... more Cooperative communication has been considered as a promising method for benefiting the advantages from MIMO (multiple-input multiple-output) system for single antenna mobiles in the wireless network, and many important milestones in this area have been achieved, ...
Uploads
Papers by Kamal Hossen