A Survey on Visual Content-Based Video Indexing and Retrieval

Hu, Weiming; Xie, Nianhua; Li, Li; Zeng, Xiaolin; Maybank, Stephen J.

doi:10.1109/tsmcc.2011.2109710

Cited by 469 publications

(58 citation statements)

References 242 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Combining the evidence obtained from several complementary classifiers can improve performance based on the literature shown in [14] and in [27].Initially, in [6] a survey of audio based music classifica- tion and annotation algorithm is obtained. Then, in [26] a survey on visual content based video indexing and retrieval shows huge information on video. In [31] a high-accurancy audio classification algorithm is proposed based on SVM-UBM using MFCCs as classification features.…”

Section: Related Workmentioning

confidence: 99%

Audio-video based Segmentation and Classification using SVM and AANN

Subashini¹,

Palanivel²

2012

IJCA

View full text Add to dashboard Cite

In this paper, we propose a method for combining audio and video for segmentation and classification. The objective of segmentation is to detect the category change point such news to advertisement. The classification system classify the audio-video data into one of the predefined categories such as news, advertisement, sports, serial and movies. Mel frequency cepstral coefficients(MFCC) are used as acoustic features and color histogram is used as visual features for segmentation and classification. Support vector machine(SVM) and autoassociative neural network(AANN) models are used for segmentation and classification. The evidence from audio and video are combined using weighted sum rule for both segmentation and classifications.

show abstract

Section: Related Workmentioning

confidence: 99%

Audio-video based Segmentation and Classification using SVM and AANN

Subashini¹,

Palanivel²

2012

IJCA

View full text Add to dashboard Cite

show abstract

“…Dynamic threshold can be selected based on mean or standard deviation of video frames or combination of both [6]. WeimingHu et al [7] and Alan Hanjalic [8] has discussed static and adaptive thresholding used in shot boundary detection techniques .This methods works well for abrupt cut detection but unable to detect gradual cut in videos. This technique is simple, easy to implement and sensitive to object or camera motion.…”

Section: Pixel Based Shot Boundary Detectionmentioning

confidence: 99%

Analysis of Popular Video Shot Boundary Detection Techniques in Uncompressed Domain

Bendale¹,

Talati²

2012

IJCA

View full text Add to dashboard Cite

Now days there are tremendous amount of videos available on internet. Entertainment video, news video, sports video are accessed by users to fulfill their different needs. Our daily routine systems are also producing huge amount of videos for example surveillance system, shopping malls, home videos etc. These videos need to be accessed for different purposes. Current research topics on video includes video abstraction or summarization, video classification, video annotation, content based video retrieval. In nearly all these application one needs to identify shots and key frames in video which will correctly and briefly indicate the contents of video. This paper compares some of the popular shot boundary detection techniques in uncompressed domain. The merits and demerits of each of the techniques are also discussed. Some experiment done are also discussed.

show abstract

“…Both text forms are important source for describing the semantic content of images [2] such as: in geo-location application, obtaining objects information, for indexing, categorizing and searching process [3]. Text extraction is an important research area [4], which comprises three stages [5]: text localization, text segmentation and text recognition.…”

Section: Introductionmentioning

confidence: 99%