Examining Robustness of Google Vision API Based on the Performance on Noisy Images

Pathak, Akshat; Ruhela, Aviral; Saroha, Anshul K.; Bhardwaj, Anant

doi:10.26438/ijcse/v7i3.8993

Cited by 3 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pengujian dilakukan dalam 5 kategori gambar, dengan total 75 sampel gambar. Penelitian ini menghasilkan kesimpulan bahwa Google Cloud Vision tidak robust terhadap gambar ber-noise[8].Google Vision API adalah layanan berbasis cloud yang memiliki salah satu fungsi utama yaitu OCR (Optical Character Recognition). OCR berfungsi untuk mengekstraksi teks dalam sebuah citra.…”

unclassified

Analisis Perbandingan Optical Character Recognition Google Vision dengan Microsoft Computer Vision pada Pembacaan KTP-el

Valentino,

Susetyo

2023

jtik

View full text Add to dashboard Cite

In this era, the need of digital data is rapidly increasing. Electronic Residental Identity Card or KTP-el is the official identity card for resident of Indonesia. One fast way to extract information on an image is by using OCR/Optical Character Recognition. Competition between Google Vision API and Microsoft Computer Vision in providing OCR service encourage companies to choose the right provider. Method conducted in this research including literature review on both OCR service provider, identification and KTP-el sample image retrieval, data grouping, code implementation and accuracy testing, result analysis and discussion, and conclusion. The result of this research show that Microsoft Computer Vision have better accuracy in reading characters in KTP-el with an accuracy percentage of 0,81% to 15,8% difference to Google Vision. Google Vision has competitive accuracy, but suffers from deficiencies when reading KTP-el with blur and noise.

show abstract

unclassified

Analisis Perbandingan Optical Character Recognition Google Vision dengan Microsoft Computer Vision pada Pembacaan KTP-el

Valentino,

Susetyo

2023

jtik

View full text Add to dashboard Cite

show abstract

Identification of human capital management policy for the officers serving in the unit in the Indian Army

Singh

Chitranshi

2023

AIP Conference Proceedings

View full text Add to dashboard Cite

Using computational systematic social observation to identify environmental correlates of fear of crime

Solymosi,

Parkinson,

Pődör

et al. 2024

Crime Sci

View full text Add to dashboard Cite

There is great importance in understanding whether people perceive an environment as safe or unsafe. Perceptions are influenced by the built environment, and through better understanding, design interventions can be made to improve the feeling of safety. There is a rich body of research on this topic, yet it requires a lot of manual effort. In this work, we present an approach named Computational Systematic Social Observation (CSSO) to automate the collection and analysis process. The approach uses Google Street View and the Google Vision API to extract characteristics (herein referred to as features) of the built environment that is used to automate the process of understanding whether people will feel fear or safety. In testing this approach, we extracted $$\tilde{1}$$ 1 ~ .3M images for the 100 locations and identified 297 features of the built environment. A measure of dependency demonstrated that some are more strongly associated with areas where people express a feeling of safety or fear. Further, through empirical testing, it is observed that these features can be used for classification. The results demonstrate the potential of the technique and were compared with human coders. The presented methodology and exploratory research provide a foundation for systematic computational observation to identify environmental correlates of fear of crime.

show abstract

Examining Robustness of Google Vision API Based on the Performance on Noisy Images

Cited by 3 publications

References 3 publications

Analisis Perbandingan Optical Character Recognition Google Vision dengan Microsoft Computer Vision pada Pembacaan KTP-el

Analisis Perbandingan Optical Character Recognition Google Vision dengan Microsoft Computer Vision pada Pembacaan KTP-el

Identification of human capital management policy for the officers serving in the unit in the Indian Army

Using computational systematic social observation to identify environmental correlates of fear of crime

Contact Info

Product

Resources

About