CMOS module house, which still enjoys the double digit gross margin in component supply chain, is one of the reasons facilitating the idea of start-up. We think this idea is practical and also profitable as we have solid network in high-tech industry, as well as comprehensive knowledge and relatively easier than others to find talent for the team up and to be one of key suppliers in the supply chain in the future. In order to make the business plan more structural, we explain the industry, product itself, market trend, market size and potential value we can earn, as well as the key names in the supply chain, including names of suppliers, competitors, and customers. Regarding to the business target, we are not aiming the goal too high to be reached. Instead, we set 3-5% of total market share (in Notebook PCs, Tablet PCs, and Smartphones) after 1-2 years business operations. We think this is practical and also profitable as the size of PC and consumer electronics (CE products) are huge, and the earnings is usually surprising even the gross margin is low, as long as the volume is huge enough.

Consider a situation where you need to identify each and every person in a room and categorize each of the persons as present or absent. To mark the presence of hundreds of people in a room takes a lot of time, which means you can eventually be left out with less time to explain the main aim of that meeting, class, or some other things. In such cases, either we may need a lot of time for a meeting or we may need more people to accomplish the tasks. In the present world, time is considered equivalent to money. If you lose your time you will lose your money. Many education institutions and offices see this as a very important consideration to maintain their busy schedule.  In this study, we came to know that many institutions and offices are facing the same issue, so as engineers we decided to take this as a challenge and try to find a solution to it. Our main objective of this project is to make a working model, which helps in marking the attendances of the person automatically and saves precious time. We can say that human effort is simply replaced by our end product which helps the person to spend more time efficiently.  To replace the human effort with an easy and cost-efficient system that has accurate results, we are using a Raspberry Pi 4 Model B as a microcontroller and along with it, we are using a Raspberry Pi camera module to capture the image of the person. To control and give the commands to the microcontroller, we are using MATLAB as a programming language that interprets the commands given by the user.   Using this Raspberry Pi system with a camera module attached to the Raspberry Pi, We can capture the image of the person who comes in front of the camera. Once the person images are captured, the microcontroller starts running the program which can predict the face of a person from the pre-trained database that we have previously stored in the system. Once the prediction is done, the face of the person is automatically marked as present in an excel sheet under the predicted name.  We are concluding that by using the automated attendance system one can avoid the manual marking of persons and save time. For further future works, one can use a good resolution camera module to capture the images clearly and can use the python coding method to access face recognition. We can also develop a mobile application, that can access the camera present in the smartphone which can be used to capture the images and mark the attendances automatically.

This thesis describes the design and subsequent implementation of a unit for traffic monitoring using Raspberry PI. First section provides a quick overview of assistance systems, which use a road lane detection techniques. Next there is a description of two diferent methods for road lane detection. Follow the description of monitoring scene. Then the work describe the practical part including the design and realization of supporting electronics, selecting of each components, including the modifying of cameras, mechanical design and creating of unit. Another section is about selection and installation of appropriate software components necessary for running of the unit and the selection of development tools for creating user application. After description of graphical user interafce, there is a description of road lanes detection algorithm. At the end of the thesis is summarized a reliability of unit in real traffic situation. At the appendix there are technical drawings, describing the unit.

This thesis deals with developing of image processing algorithm for robots controlled by informations taken from visual system. Core of the used system constitutes low-budget platform Raspberry Pi. Before the development of algorithm there is a series of test for image processing which discovers possibilities of used platform. Problem solution is divided to several parts. Limited performance frequently leads to individual problem solving. Afterall is shown sensitivity and performance analysis of developed solution.