direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Logo der TU Berlin

Details zu Abschlussarbeiten

Zur ‹bersicht


Developing a GUI for Smart Clothing Recommender Application (Dress Me Up) in IOLITE


Bachelor Thesis

The project aims at developing an application that finds and retrieves available clothing being sold online to the user matching the style of the user. The most important part of the application will be the smart clothing detection module which detects the clothing on an uploaded photo or from the image captured by a camera (e.g. shirt, trousers, bag etc.) and describe each of these clothing w.r.t their colors, textures and outlines autonomously.

Thesis Work Description:

This part of the project will only focus on designing a GUI Application, which will be responsible for introducing a user friendly interface retrieving the similar clothes worn by the user from the popular shopping websites. The GUI will introduce interfaces for text-searching, speech commands and uploading a photo (uploaded photos will be processed by another module). The project will be composed of two essential modules:
I) First module, Dress Me Up App GUI (DM-GUI), should allow user to use the application by entering type, color, texture and outline of the clothes manually or via speech commands, or adding a similar photo of the cloth. It should be noted that the uploaded photos will be sent to the Clothing Detection System (CDS, another module to be implemented by another student) which will output again the textual information of the clothing for text-searching. The GUI requires the following tasks:
1. Designing an IOLITE application, which enable manual searching for the clothes by text-searching, speech commands (Google Speech API) or uploading a photo.
2. Designing an interface to show the resulting similar clothing images, to the user and allowing the user to sort the results w.r.t their prices.
3. Establishing web socket communication between CDS platform and IOLITE HW platform for fetching cloth descriptive labels (texts) and sending the uploaded photo by the user.
4. Collating found similar cloth web results via Cloth Searching Engine Module (CSEM) and show them user.
II) Second module, CSEM, will enable searching for the clothes on the shopping websites. As mentioned above, the search will only be in text format whatever the input method the user chooses (i.e. manual entry, speech, uploading a photo). This module will be implemented as a sub-module under the above-mentioned GUI application and will require the following tasks:
1. An extensive research of the available local websites for online-shopping. An analysis of how to make the auto-search over these websites, such as, using their APIs if any, using their search engines etc.
2. Retrieving the resulting images after the search, embedding their corresponding links to the image. In other words, the retrieved images will be shown to the user over DM-GUI, and if the user would like to see the details, touching on the image will direct the user to the source web page.
3. The prices, original names, and specifications of the search results will also be forwarded to DM-GUI module.


Projekt Datei:  BA GUI.pdf

Diplomarbeit Datei:  


Betreuer:  Cem Akpolat
Email:   cem.akpolatgt-arc.com


Noch Offen