Mini MATLAB Projects

Human Age and Gender Estimation using Convolutional Neural Network and Image Processing

The objective of this project is to develop a reliable and accurate system for human age and gender estimation using convolutional neural network (CNN) and image processing techniques. The main goal is to design a model that can accurately estimate the age and gender of individuals based on their facial features.

In recent years, age estimation and gender classification were one of the issues most frequently discussed in the field of pattern recognition and computer vision. This project proposes automated predictions of age and gender-based features extraction from human facials images. Contrary to the other conventional approaches on the unfiltered face image, in this study, we show that a substantial improvement be obtained for these tasks by learning representations with the use of the deep convolutional neural networks (CNN). The convolutional neural network method used in this research enhances robustness for highly variable unconstrained recognition tasks to identify the gender and age group estimation. This research was analyzed and validated for the gender prediction and age estimation on the face dataset from different sources. The results obtained show that the proposed approach offers a major performance gain, our model achieve very interesting efficiency and the state-of-the-art performance in both age and gender scoring.

Talk to Expert   Submit Assignment

Applying a Random Projection Algorithm to Optimize Machine Learning Model for Breast Lesion Classification

Since computer-aided diagnosis (CAD) schemes of medical images usually computes large number of image features, which creates a challenge of how to identify a small and optimal feature vector to build robust machine learning models, the objective of this study is to investigate feasibility of applying a random projection algorithm (RPA) to build an optimal feature vector from the initially CAD-generated large feature pool and improve performance of machine learning model. We assemble a retrospective dataset involving 12 cases of mammograms have benign and malignant lesions. A CAD scheme is first applied to segment mass regions and initially compute 181 features. Then, support vector machine (SVM) models embedded with several feature dimensionality reduction methods are built to predict likelihood of lesions being malignant. All SVM models are trained and tested using a cross-validation method with various folds of 10, 5 and 3. SVM generates a likelihood score of each segmented mass region depicting on one-view mammogram. By fusion of two scores of the same mass depicting on two-view mammograms, a case-based likelihood score is also evaluated.

Talk to Expert   Submit Assignment

A Matlab Project in Optical Character Recognition (OCR)

The process of OCR involves several steps including segmentation, feature extraction, and classification. Each of these steps is a field unto itself, and is described briefly here in the context of a Matlab implementation of OCR.

A few examples of OCR applications are listed here. The most common for use OCR is the first item; people often wish to convert text documents to some sort of digital  representation.
1. People wish to scan in a document and have the text of that document available in a word processor.
2. Recognizing license plate numbers
3. Post Office needs to recognize zip-codes

Talk to Expert   Submit Assignment

A Zigbee Based Wireless Sensor Network for Sewerage Monitoring using MATLAB

Blockages in sewers are major causes of both sewer flooding and pollution. Water companies which fail to tackle this problem face hefty fines and high operational costs if they unsuccessful to provide a practical solution to prevent flooding. As a result, the detection of sewer condition is routinely required to inform on the best course of action to eliminate this critical problem. This paper presents a novel low cost wireless sensor technology to detect blockages proactively, and feed these event data back to a central control room. The practical deployment of the proposed WSN in an urban area will be demonstrated. In addition, the challenges of this technology in a field trial and the recorded data in terms of the sensor and communication reliability will be addressed

Talk to Expert   Submit Assignment

Traffic Light Control System using MATLAB

Loop detectors provide accurate and reliable traffic light control. Two inductive loop detectors are cut into each lane, just before and just after the stop line. Every passing vehicle is registered. A delay time can be set. Any vehicle that passes after that time is photographed twice in quick succession. The first photo shows the offence, the second confirms that the vehicle was actually moving. The camera is set up so that the red light is also visible in the picture. Loop detection distinguishes between cars and trucks. A separate speed threshold can be installed for each category. The traffic light camera's can also be used to measure speed when the lights are showing green, red or amber.

Talk to Expert   Submit Assignment

A Bi-directional Visitors Counter using MATLAB

This counter can be used to know the number of visitors present in the room at any given time. It is useful for places such as movie halls, buldings and offices. To keep the cost low it uses simple calculator instead of a counter-and display circuit. The calculator can be used as a normal calculator is plugging it off from the circuit. All the components are readily available in market and the circuit is easy to build.

Talk to Expert   Submit Assignment

Bomb Detection Robotics Using Embedded Controller using MATLAB

Detect the bomb by sending the robot to the respective place. A person can operate the system from personal computer through wireless RF control. The operator can control the system by visual moving pictures transmitted from the robotic system. If it senses there is a bomb means it gives the buzzer sound will be generated by the robot. It always possible that when influenced by destructive metals, it may lead to severe damages. For this purpose we configure a circuitry for metal detection in our project .

Talk to Expert   Submit Assignment

Intelligent Alcohol Detection System for CAR using MATLAB

This is used to Sense and drive the relay for ignition on/off for drug drive control system.

Talk to Expert   Submit Assignment

Centrally Controlled Multichannel Token Display using MATLAB

It might have observed at various places where numerous counters are there, you are always confused as to which queue you should select to get your work done. In usual cases you select the smallest queue and end up leaving the counter late. By utilizing this system the inordinate delay in transacting your business can be overcome since you need not have to stand in any queue. You can deport after finishing your job much earlier than expected. This is again very highly useful and cost effective project.

Talk to Expert   Submit Assignment

Microcontroller Based Cellular Voting Machine using MATLAB

In this modern world people are forced to use electronic devices in their daily life. Now day's electronic voting machines are used for election. Here we introduced a cellular voting machine based on micro controller. In this system there are two units, a master unit and a voting unit. The voting unit is placed anywhere and the master unit is placed in a control room. The voting unit contains a DTMF coyer, which generates a DTMF tone and is transmitted to the master unit through the FM transmitter. The master contains a FM receiver, DTMF decoder, Micro controller and Display units. The tone from the voting unit is received by the receiver and is decoded and specific functions are carried out by micro controller and then it is displayed.

Talk to Expert   Submit Assignment

Card Based Security System using MATLAB

This is a microprocessor based security system capable of identifying cardholders with references to name. Further the access to any given point is controlled by individual passwords for individual cardholders. In case of entry of wrong password the system will give audio alert. This is highly secure and cost effective project, which can be, implemented at various security zones.

Talk to Expert   Submit Assignment