TARU PUBLICATIONS
Journal of Statistics and Management Systems cover

Journal of Statistics and Management Systems

(Since 1998)
Hybrid ·Peer-reviewed·ISSN (Online): 2169-0014·ISSN (Print): 0972-0510

Indexed in ABDC Australia

Powered by:Powered by

Monthly Journal: Publishes peer-reviewed aticles on theoretical and applied statistics and management systems, expoloring industrial statistics, actuarial and decision sciences.

Issues up to 2022 co-published with and available at:Taylor & Francis Online
submissions@tarupublications.com
Taru Online First Current IssueSpecial IssuesBrowse all Issues
Journal of Statistics and Management Systems
Open Access Research Article

An optimized statistical framework for adaptive shot boundary detection and key frame extraction in video streams

* ,

* Corresponding author · click or hover a name for details

pp. 629–659Vol. 29Issue 6June 2026DOI: 10.47974/JSMS-1605XML
Received:
01 Aug 2025
Published Online:
08 Apr 2026
Article type:
Research Article
Language:
EN
Article no.:
JSMS-1605
Pages:
629–659

Abstract

The rapid growth of regional language news videos faces major challenges for efficient indexing and retrieval, particularly for regional languages such as Gujarati, which is spoken by 55 to 62 million people worldwide. Processing every frame in videos is time-consuming and redundant; therefore, accurate shot boundary detection followed by effective key-frame selection is important for text-based video retrieval. This research presents an adaptive video segmentation framework for Gujarati news videos that integrates shot boundary detection with key frames selected using statistical methods. Initially, consecutive video frames are processed category-wise, and six frame-level features are extracted from the videos, such as PDM, CDM, HBA, Gabor response, ECR, and EED. These features are then normalized and fused using a weighted approach. Mean and standard deviation based adaptive thresholds are then applied to detect both abrupt and gradual shot transitions. For the detected shots, a key frame has been extracted from shots containing Gujarati text based on the Ground truth table. This approach uses entropy and edge density to capture detailed information and structural variation. Adaptive thresholds derived from their mean values are used to preserve descriptive frames with high textual significance. Experimental evaluation on TV9 Gujarati news video datasets shows that the proposed framework effectively reduces redundant frames while preserving semantically significant content key frames, which are suitable for efficient Gujarati text-based video retrieval. Total no. of shots reduced is 2158 from 80675, and total key frames are 901, with the lowest accuracy in the weather category, with 81.0714 % and the highest recorded as 88.00 % for the Cricket category.

Keywords

Shot detectionMCA-EUEntropyEdge density

Subject Classifications

Primary 68U10Secondary 68P2094A08

References

[1] B. T. Truong and S. Venkatesh, “Video abstraction: A systematic review and classification,” ACM Trans. Multimedia Comput. Commun. Appl., vol. 3, no. 1, pp. 3 (2007). https://doi.org/10.1145/1198302.1198305  
[2] Y. Zhai and M. Shah, “Visual attention detection in video sequences using spatiotemporal cues,” in Proc. ACM Int. Conf. Multimedia, Singapore, 2005.  https://doi.org/10.1145/1180639.1180824  
[3] C. B. A. Sai Ram and S. Sharma, “Video segmentation: A systematic review on recent advances, techniques, and classification,” in Proc. Int. Conf. Advances in Computing, Communication Control and Networking (ICACCCN), Greater Noida, India, pp. 615–620 (2018).  https://doi.org/10.1109/icacccn.2018.8748578  
[4] T. Kar, P. Kanungo, and S. N. Mohanty, “Video shot-boundary detection: Issues, challenges, and solutions,” Artif. Intell. Rev., vol. 57, pp. 104 (2024). https://doi.org/10.1007/s10462-024-10742-1  
[5] U. Gargi, R. Kasturi, and S. Strayer, “Performance characterization of video-shot-change detection methods,” IEEE Trans. Circuits Syst. Video Technol., vol. 10, no. 1, pp. 1–13 (2000).  https://doi.org/10.1109/76.825852   
[6] Y. Bendraou, F. Essannouni, D. Aboutajdine, and A. Salam, “Video shot boundary detection method using histogram differences and local image descriptor,” in Proc. World Conf. Complex Systems (WCCS), Marrakech, Morocco, pp. 665–670 (2014). https://doi.org/10.1109/icocs.2014.7060883  
[7] W. Tong, L. Song, X. Yang, H. Qu, and R. Xie, “CNN-based shot boundary detection and video annotation,” in Proc. IEEE Int. Symp. Broadband Multimedia Systems and Broadcasting, Ghent, Belgium, pp. 1–5 (2015). https://doi.org/10.1109/bmsb.2015.7177222  
[8] S. N. Kumar, V. S. K. Reddy, and L. K. Balivada, “Content-based video retrieval using deep learning algorithms,” in Intelligent Systems and Sustainable Computing (ICISSC 2022), Smart Innovation, Systems and Technologies, vol. 363, Springer, Singapore, (2023) https://doi.org/10.1007/978-981-99-4717-1_52  
[9] R. M. Bommisetty, P. Palanisamy, and A. Khare, “Content-based video retrieval—methods, techniques, and applications,” in Advances in Soft Computing Techniques in Data Science, IoT, and Cloud Computing, Studies in Big Data, vol. 89, Springer, Cham (2021). https://doi.org/10.1007/978-3-030-75657-4_4   
[10] E. M. Saoudi and S. Jai-Andaloussi, “A distributed content-based video retrieval system for large datasets,” J. Big Data, vol. 8, p. 87 (2021). https://doi.org/10.1186/s40537-021-00479-x  
[11] M. J. Esteve Brotons, F. J. Lucendo, R.-J. Javier, and J. Garcia-Rodriguez, “Shot boundary detection with 3D depthwise convolutions and visual attention,” Sensors, vol. 23, no. 16, p. 7022 (2023). https://doi.org/10.3390/s23167022  
[12] T. Soucek and J. Lokoc, “TransNet V2: An Effective Deep Network Architecture for Fast Shot Transition Detection”, in Proceedings of the 32nd ACM International Conference on Multimedia, 28 October (2024). https://doi.org/10.1145/3664647.3685517 .
[13] Sadiq Abdulhussain. Abd Ramli, M. Saripan, Basheera Mahmmod, Syed Al-Haddad, Wissam Jassim, “Methods and challenges in shot boundary detection: A review,” Entropy, vol. 20, pp. 214 (2018). https://doi.org/10.3390/e20040214  
[14] B. A. Halim and T. Faiza, “Shot boundary detection: Fundamental concepts and survey,” in Proc. Conf. Innovative Trends in Computer Science (2019).
[15] A. Shah and D. Mishra, “A review of biometrics modalities and data mining algorithm,” in Ambient Communications and Computer Systems, Adv. Intell. Syst. Comput., vol. 696, Springer (2018). https://doi.org/10.1007/978-981-10-7386-1_51  
[16] TV9 Gujarati News Channel, “Gujarati news video dataset,” TV9 Gujarati, accessed Oct. 12 (2024).
[17] S. Meng and H. Jiang, “The video shot boundary cut detection based on color histogram,” Journal of Computational and Theoretical Nanoscience, vol. 13, no. 5, pp (May 2016). https://doi.org/10.1166/jctn.2016.4975   
[18] H. Zhang, A. Kankanhalli, and S. W. Smoliar, “Automatic partitioning of full-motion video,” Multimedia Syst., vol. 1, pp. 10–28 (1993). https://doi.org/10.1007/bf01210504  
[19] Z. Li, X. Liu, and S. Zhang, “Shot boundary detection based on multilevel difference of colour histograms,” in Proc. Int. Conf. Multimedia and Image Processing (ICMIP), pp. 15–22 (2016). https://doi.org/10.1109/icmip.2016.24    
[20] Shitao Tang, Litong Feng, Zhangkui Kuang, Yimin Chen and Wei Zhang, “Fast Video Shot Transition Localization with Deep Structured Models”, Lecture Notes in Computer Science,Asian Conference on Computer Vision (2019), https://doi.org/10.1007/978-3-030-20887-5_36
[21] Yogya Tewari, Payal Soni, Shubham Singh, Murali Saketh Turlapati, and Avani Bhuva, “Real time sign language recognition framework for two way communication,” in Proc. ICCICT, pp. 1–6 (2021). https://doi.org/10.1109/iccict50803.2021.9510094  
[22] A. Adnan and M. Aliaeda, “Shot boundary detection using sorted color histogram polynomial curve,” Life Sci. J., vol. 10, pp. 1965–1972 (2013).
[23]A. Shah and V. A. Bharadi, “Performance analysis of soft biometrics features for dynamic signature recognition using complex Walsh plane based feature vector,” in Proc. ICCICT (2015). https://doi.org/10.1109/iccict.2015.7045719  
[24] M. Verma and B. Raman, “A hierarchical shot boundary detection algorithm using global and local features,” in Proc. Int. Conf. Computer Vision and Image Processing (2017).  https://doi.org/10.1007/978-981-10-2107-7_35  
[25] A. Gushchin, A. Antsiferova, and D. Vatolin, “Shot boundary detection method based on a new extensive dataset and mixed features,”  Proceedings of the 31th International Conference on Computer Graphics and Vision. Volume 2 (2021). https://doi.org/10.20948/graphicon-2021-3027-188-198  
[26] P. K. Sahoo, S. Soltani, and A. K. C. Wong, “A survey of thresholding techniques,” Comput. Vis. Graph. Image Process., vol. 41, no. 2, pp. 233–260 (1988).  https://doi.org/10.1016/0734-189x(88)90022-9  
[27] S. A. Rajesh, V. A. Bharadi and P. Jangid, “Performance improvement of complex plane based feature vector for online signature recognition using soft biometric features,” 2015 International Conference on Communication, Information & Computing Technology (ICCICT), Mumbai, India, pp. 1-7 (2015). https://doi.org/10.1109/iccict.2015.7045719   
[28] A. Bhuva and D. Mishra, “Gujarati optical character recognition using efficient text feature extraction approaches,” Informatica, vol. 49 (2025).  https://doi.org/10.31449/inf.v49i28.8341  
[29] Jasmin T. Jose, S. Rajkumar, Muhammad Rukunuddin Ghalib, Achyut Shankar, Pavika Sharma, and Mohammad R. Khosravi, “Efficient shot boundary detection with multiple visual representations,” Mobile Inf. Syst., vol. 2022, Art. no. 4195905 (2022).  https://doi.org/10.1155/2022/4195905  
[30] N. Ibrahim and Z. Abduljabbar, “Video shot boundary detection based on frames objects comparison and scale-invariant feature transform technique,” Comput. Sci. Inf. Technol., vol. 5, pp. 130–139 (2024). https://doi.org/10.11591/csit.v5i2.pp130-139  
[31] Z. Yang, L. Tian, and C. Li, “A fast video shot boundary detection employing OTSU’s method and dual pauta criterion,” in Proc. IEEE Int. Symp. Multimedia, pp. 583–586 (2017). https://doi.org/10.1109/ism.2017.114   
[32] Rui Liang, Qingxin Zhu, Honglei Wei, and Shujiao Liao, “A video shot boundary detection approach based on CNN feature,” in Proc. IEEE Int. Symp. Multimedia, pp. 489–494 (2017).  https://doi.org/10.1109/ism.2017.97  
[33] S. Dhiman, R. Chawla, and S. Gupta, “A novel video shot boundary detection framework employing DCT and pattern matching,” Multimedia Tools Appl., vol. 78, no. 24, pp. 34707–34723 (2019). https://doi.org/10.1007/s11042-019-08170-3  
[34] M. Phatak and M. Patwardhan, “Mathematical modelling and statistical analysis in designing deep learning-based shot boundary detection and aesthetic assessment of videos,” J. Interdisciplinary Math., vol. 27, no. 2, pp. 369–382 (2024). https://doi.org/10.47974/jim-1857  

Views: 132Downloads: 96Citations: 0