One of the most difficult task for the students is to decide their project. Many student come to me and ask, “Sir, please suggest me some project”. There are many areas from which student can take project. In this post we are going to discuss some project ideas taken from the deep learning.
1. Hand Gesture Recognition Using CNN
Hand gesture recognition has received a great deal of attention in recent years. The potential application of it is mobile technology, gaming systems and real time imaging technology.
2. Garbage Classification
We can classify the garbage into different recycling categories so the we can process waste efficiently. For example garbage can be classified into Glass, Paper, Metal, Plastic. For more detail study the following report: Classification of Trash for Recyclability Status.
3. Age Detection from the Image
We can predict the age of the person from his or her facial attributes. One of the most challenging dataset is available at IMFDB Dataset. The Indian Movie Face Dataset (IMFDB) is created by IIIT Hyderabad. (IMFDB) is a large unconstrained face database consisting of 34512 images of 100 Indian actors collected from more than 100 videos. All the images are manually selected and cropped from the video frames resulting in a high degree of variability in terms of scale, pose, expression, illumination, age, resolution, occlusion, and makeup. IMFDB is the first face database that provides a detailed annotation of every image in terms of age, pose, gender, expression and type of occlusion that may help other face related applications.
4. Driver Distraction Detection
Given the images of the driver while driving the car we can detect the different action of the driver like messaging, eating, talking etc and based on these action we can detect while his driving is safe or not and alarm him.
5. Handwritten Text Recognition
We can implement a handwritten character recognition system that can extract handwritten text data from the scanned image.
6. Image Caption Generation
Image caption is the task where given an image system generate a caption that describe the content of the image. The step of image caption generation is given below:
- Detect the objects in photograph and generate labels for those objects.
- The next step is combine those label in coherent sentence descriptions.
Generally, the systems involve the use of very large convolutional neural network for the object detection in the photographs and then a recurrent neural network like an LSTM to turn the labels into a coherent sentence.
7. Plant Leaf Recognition
Automatic plant species recognition with image processing has application in weeds identification, species discovery, plant taxonomy, natural reserve park management.
In the Future we add more suggestion for the project. If you have any interesting idea please write in the comment of this post. If you have any question or suggestion feel free to share.