Jian-Kun Wang
University of Electronic Science and Technology of China (UESTC)
Department of Computer Science
Email: jiankunwang62442@gmail.com

 

RESEARCH EXPERIENCE

Automatic Image Captioning , July 2019-Sept. 2019
Data Analysis , June 2018-Sept. 2018

PROJECTS

Research Experience

Automatic Image Captioning
Tools : Python(TensorFlow, PyTorch)

Abstract:

This research investigated captioning papers based on the attention mechanism and replicate the result of the latest research. The performance of each
algorithm was tested on the data set.

Description:

  • Explored the mechanism of RNN , implement seq2seq model.
  • Replicated the results of the paper which use the memory module to memorize the knowledge about language style, and implement the generation of
image captioning text in a specific language style.
  • Investicated attention based image captioning mechanism, using encoder-decoder in the form of weighted local visual features to generate a
description. The survey results show the attention widely thought to use, can not only add it to decoder, but also encoder.

Future :

The current image description opens up many new research directions, such as adding style elements. Current datasets are mainly trained and tested
based on natural images, and it is expected that image description methods for remote sensing images and even medical images will be proposed in the
future.
 

Data Analysis
Tools : MATLAB, Python

Abstract:

Classical statistical machine learning and graph probability models are used to process image data, and various supervised and unsupervised algorithms
are implemented. The tests are performed on real data sets, and the algorithm performance is compared and analyzed.

Description:

  • Image data pre-processing. Programs in MATLAB are used to implement image coordinate conversion, gray mapping, histogram correction, and spatial filtering, and test on real data sets.
  • Target Detection. SIFT corner detection technology is implemented in Python and tested on real images.
  • Image pattern recognition. The Back Propagate Network and CNN was implemented to classify the handwritten data set MNIST . After PCA dimensionality reduction, optimization of the loss function and learning rate, the classification accuracy rate of 97.3% by BP Network adn 99.2 by CNN was finally
obtained .
  • Compared the classification differences of SVM model, Tree Model and CNN on cat and dog dataset(on Kaggle). It is found that when the sample data volume reaches 3000 , the classification accuracy of SVM and Tree Model decreases significantly, and the classification effect of CNN network is stable.
 

Projects

Abstract:

This project originated from an observation with my partners: In the university's teaching buildings,
libraries, and other public places, it is often the case that the room is empty but the air conditioner is still
running. We hope to propose a thermostatic system to avoid such a waste of resources.
 
This project proposes an intelligent indoor constant temperature control system, which can automatically
control heating, ventilation and air conditioning equipment (such as air conditioners, electric heaters, etc.), and keep the indoor temperature at a comfortable temperature under the condition of the lowest energy
consumption . 
 
项目1-4

Abstract:

    " In addition to posing easily, you can also take photos with realistic virtual characters across time
     and space . "
 
In the era of the mobile Internet, images have become an important medium for disseminating
information, and the emergence of generations of camera software has greatly satisfied people's
needs for recording and sharing lives. Based on market research, our team has co-designed a new
generation of camera software . We mainly solve the following problems:
 -  Unique and beauty are the most concerned about the photographer
 -  Geographical separation makes it impossible to take photos with family and friends together
 -  There is no easiest way to edit the photo
 
项目2-3

Abstract:

With the continuous expansion of the domestic e-commerce industry, the market
competition of the logistics industry has become increasingly fierce. How logistics
companies can effectively integrate user needs and rationally allocate logistics resources,
reduce product inventory, and accelerate response to the market. This is a problem faced by all
logistics companies.
 
 
项目3-2

Abstract:

In VS2015 development environment, computer graphics and Windows
programming knowledge ws used to achieve a user-friendly and easy-to-use drawing
software called "Sketchpad". The drawing software can provide the following functions:
1. Basic graphics drawing: rectangle, polygon, ellipse, circle, etc.
2. Interactive curve drawing: Provide Bezier curve drawing function, can call graphic function, and
have multiple control point parameter selection.
3. Graphic fill: two graphic fill algorithms can be provided — scan line fill algorithm, flood fill
algorithm to fill primitives, and allow users to set.
4. Graphic file management functions, including new, open and save functions.
5. Eraser function to erase graphics on the drawing board.
 
pro4