DOWNLOAD FREE PROJECTS | ENGINEERING NOTES | PLACEMENT NOTES | MATLAB AND ANDROID PROJECTS

Translate Images on Android Device OUTPUT Motivation: Currently, when a user needs to know the meaning of a segment of text in his native  language, he usually needs to manually type the text into a dictionary or search engine to get  the translation. This can be a huge burden if there is a lot of text. Some apps can extract text  using OCR and show the aggregated translation to user. While this reduce the trouble in typing  the text, its result doesn’t show the positional information of the text. For example, if a user is  studying the map of the United states, it would give an output of all the name of the states, concatenated. However, the location of the words are missing and it is unintuitive for user to  know where each state is. We want to build an Android app that can not only recognize text, but also overlap the  translated text on top of the original text, thus preserve the location information. We believe this  app would be useful in everyday life for foreign v

Automated  Study of Greek Coins via Cluster Analysis OUTPUT Background One of the tools historians use when trying to understand the economies of ancient civilizations is the die study. Researchers pore over collections of coins from a particular region and attempt to determine which coins were created from the same engraving (die). From the number of dies in use in a region, these researchers can extrapolate about the economic health of the region at that time. If each die depicted a completely different person or animal, the sorting process would be simple, but often coins will feature the same subject, even if they come from different dies. Since the dies were made by hand, no two dies were identical, but sometimes the differences can be as subtle as the shape of the nose or eye, details on the helmet, or the number of leav

✔️Using Image Processing to Identify and Score Darts thrown into a Dartboard ✔️Introduction The game of darts is a throwing sport in which participants toss projectiles into a circular target  attached to a vertical surface. The target is divided into many regions which correspond to different point and multiplier values. Darts is commonly played across North America and Europe and is a popular past time for many so an application that allows players to more conveniently keep score would be widely  beneficial. “Darts” is a general term for a targeting game following this basic premise and many game variations exist within this archetype; all utilizing the standard dart projectiles with a regulation dart board. Each game variant may have different objectives for which players to aim but identifying the region in  which the dart has hit in the dartboard is necessary for proper scoring. This project proposes the use of image processing to identify thrown darts and to det

✔️P hotographic images based on perceived aesthetic quality ✔️ OVERVIEW Aesthetics in photography are highly subjective. The average individual may judge the quality  of a photograph simply by gut feeling; in contrast, a photographer might evaluate a photograph  he or she captures vis­a­vis technical criteria such as composition, contrast, and sharpness.  Towards fulfilling these criteria, photographers follow many rules of thumb. The actual and  relative visual impact of doing so for the general public, however, remains unclear.  In our project, we will attempt to show that the existence of certain characteristics does indeed  make an image more aesthetically­pleasing in general. We plan to achieve this by way of  machine learning and digital image processing techniques by building a learning pipeline that  generates a hypothesis that classifies images as exhibiting high levels of aesthetic quality or  not. The potential impact of building a system to solve this prob

✔️Virtual Graffiti  ✔️ Project Description: The goal of this project is produce an augmented reality system where a user may select some distinguishable, flat, rectangular, mostly uniform-colored object (e.g. a piece of paper) in a live video feed and overlay a desired image onto that selected surface. ✔️Motivation: This project has uses in previewing images as they might appear on a surface such as a piece of paper, a poster, a billboard, etc. It can also used as an aid for aspiring artists to learn the basics of drawing, as they can overlay a selected image on a piece of paper and trace its outline--especially if the image has been passed through an edge detector. ✔️Methods: To initially identify the flat surface, we will use the Android device’s touch screen capability to allow the user to make a selection on the live feed. The flat object will be segmented using color thresholding and then isolated using a connected components algor

✔️ Automatic number plate recognition ✔️ Introduction: Automatic number plate recognition (ANPR), also known as automatic license plate reader, was  invented in 1976 in at the Police Scientific Development Branch in the UK and now widely used  in police forces worldwide. It involves many fundamental digital image processing techniques  including match filtering, edge detection, character recognition, and so on, to make it a great  topic for entry level practice. Also it is still an active topic nowadays to solve new challenges  such as reliability over different illumination and other environmental condition, accuracy of  the recognition, and also from lower-resolution images as the computing hardware gets  cheaper and ANPR goes to more people beyond the police forces. ✔️Goal: This project is not to compete with existing commercial softwares for road-rule enforcement cameras or closed-circuit television to make it more robust under different environmental cond

✔️ Stereoscopic 3D Reconstruction Using Keypoint Detection ✔️Introduction This project aims to improve on existing methods for 360° stereoscopic image reconstruction by utilizing multiple perspectives of panoramic images stitched from fisheye lenses. Based on translation input from a user wearing a head mounted display, we can use a combination of depth estimation, image warping and keypoint detection to reconstruct 3D views  without excessive use of computationally expensive inpainting algorithms. By estimating which  camera capture location maps to a user’s translation, and matching image features close to image  areas that need inpainting, we hope to achieve fast, if not real­time 3D stereoscopic  reconstruction of real world scenes.  Figure 1: After detecting foreground and background components using a depth map, we  Encounter areas that were hidden in the original perspective. Because inpainting is costly and  inaccurate, incorporating data from different perspe

✔️Random Undersampling Methods for Spatio-Temporal Sparse Dynamic MRI ✔️1 Introduction This topic was proposed by Prof. John Pauly as a combined project for EE368 (Digital Image Processing) and EE369C (Medical Image Reconstruction). ✔️2 Theory Compressed sensing in MRI typically takes advantage of sparsity in the image or an image-transform space  in order to accelerate scan times without loss of image information [1]. Recent research has extended these approaches to take advantage of not only spatial sparsity (via the wavelet but also temporal sparsity in  dynamic MRI acquisitions. Dynamic MR images contain redundant information in both space and time, allowing representation with few sparse transform coefficients [2]. Whereas uniform undersampling results in coherent aliasing, appropriately designed random under-  sampling methods produce incoherent aliasing, which appears noise-like in image reconstructions. Com- pressed sensing in dynamic MRI utilizes

✔️Signboard Character Recognition ✔️Motivation Imagine a world in which a person can walk down any street and take a picture of a random store’s signboard with a mobile device, enabling him or her to know what goods or service the store  provides, the ratings of the store, his or her geolocation, and even suggestions on nearby shops that may  interest him or her. ✔️ Goal We will specifically tackle the problem of the signboard character recognition. Although OCR  has been around for a while and is now commonly used to convert scanned documents [3] and license  plate [1] to text, the problem we are tackling here is more interesting. Specifically, the signboard can be  of different color, the signboard text can be non-standard, the signboard image can be taken at an angle,  and the exterior of the signboard has to be removed when performing OCR. ✔️Our Initial Thought on Implementation 1. Input of the original (RGB) image. 2. Convert the image to grayscale.

✔️ Obstacle avoidance with stereo vision in Self-driving cars ✔️Motivation Autonomous vehicles are the future of mobility and to realize this future, the costs associated with the  current technology have to be reduced significantly. Most autonomous vehicles use lidar systems, with prices  in the range of $60,000-$80,000, for perception. An alternative to lidar systems for perception are cameras  and vision systems. Vision systems are comparatively inexpensive but are not nearly as accurate as lidar  systems. As part of this project, we plan to explore the potential of vision systems to detect obstacles using  stereo vision. ✔️Description The plan is to implement a simple obstacle detection program and test it on an existing self driving car.  The current self driving car we plan to do our tests on is X1, Stanford’s student built drive by wire, steer  by wire test vehicle. The two major stages that constitute the technology of an autonomous vehicle are 1) Percept