Content/Text Extraction

Description: Extract and save contents from PDF, Word and PPT files. Contents include the following:  Letters, numbers, Chinese characters and characters from other languages (e.g. Russian, French and German etc.)  Sheets/tables (with data), structured tables etc.  Pictures, which may includes company LOGOs and products; Ensure that the entire file is correctly extracted and saved. Functional Requirement:  Characters to be recognized at 99% accuracy level;  Tables/sheets to be recognized at 95% accuracy level;  Recognizing both Chinese and English characters are required at the first stage;  Multilingual (e.g. Russian, German, French etc.) will be extended later on (terms and dates here are further-negotiable).  We prefer the code to be written on Java or Python, while others are also acceptable Input & Output:  Support selecting source files as inputs, which include selection of folders, files and files content.  Output method: export and save files to folders as required  Have a graphic UI and API Skills Required:  To be familiar with parsing PDF, Word and PPT files, similar coding experience is required;  It would be an advantage, if DEMO or similar software/tool/program is provided  Payment issues will be negotiated with selected candidates