Browsing by Author "Lin, Chang-Hong"

Now showing 1 - 2 of 2

Acoustic Scene Change Detection by Spectro-Temporal Filtering on Spectrogram using Chirps
(2016)
Lin, Chang-Hong
;
Cheong, Kah-Meng
;
Huang, Mao-Chang
;
Chen, Ming-Yen
;
Chang, Chen-Kuei
Indoor acoustic scene change detection systems using periodic impulse signals were developed in the past. Comparing with impulse signals, the chirp signal is more robust against environmental noise due to its specific spectro-temporal structure, which can be easily detected using a spectro-temporal modulation filtering mechanism. In this paper, we demonstrate a system which employs the two-dimensional spectro-temporal filtering mechanism on Fourier spectrogram to measure the total energy of reverberations of the chirp signal and compares the energy difference between consecutive chirps with a predefined threshold to automatically detect the change of the acoustic scene. Simulation results show the proposed system is very effective in detecting the acoustic scene change in a real living room with great robustness against noise recorded from real-world.
Clothing Recommendation System based on Visual Information Analytics
(2019-01-01)
Lin, Yun-Rou
;
Su, Wei-Hsiang
;
Lin, Chub-Hsien
;
Wu, Bing-Fei
;
Lin, Chang-Hong
Due to the short fashion style life circle, much more different clothing designs show up. It is hard for consumers to find the suitable clothes effectively. To solve this problem, an automatic and reliable recommendation system is in great demand. In this paper, the clothing attributes recognition, gender recognition, and body height are considered to design the recommendation system. Based on the clothing style, gender and body height, the system can recommend the proper clothes with suitable size. On-line texture modeling is proposed to produce the variation of the clothing texture so that the recommendation system can give reasonable and diversified choices for the consumers. Besides, the data of consumers' wearing style is also useful to make the better marketing strategy. According to the reasons above, the clothing recognition and recommendation system can create a win-win situation between the consumers and the fashion industry.