SIFT Matching with CNN Evidences for Particular Object Retrieval

Zhang, Guixuan; Zhang, Zhi; Zhang, Shuwu; Zhang, Yuan; Wu, Wei

doi:10.1016/j.neucom.2017.01.081

Cited by 30 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While it is used as an appended feature to the conventional features directly for the image matching, the retrieval accuracy is influenced obviously by the quality of CNN features. The experimental results show that our proposed strategy is evidently better for this task than those of Zhang et al [53] and Zheng et al [52].…”

Section: Cscfm Retrieval and Comparison On Oxford Buildings Datasetmentioning

confidence: 73%

Large Scale Category-Structured Image Retrieval for Object Identification Through Supervised Learning of CNN and SURF-Based Matching

Yang

2020

IEEE Access

View full text Add to dashboard Cite

In the modern era of Internet, mobile and digital information technology, image retrieval for object identification, just as wine label retrieval from a wine bottle image, has become an important and urgent problem in artificial intelligence. In comparison with the general image retrieval, it is rather challenging because there are a huge number of object identification or brand images which are very similar and difficult to discriminate, and the number of different brand images in the given dataset changes greatly, that is, the samples are strongly unbalanced for these brands. In this paper, we propose a CNN-SURF Consecutive Filtering and Matching (CSCFM) framework for this kind of image retrieval, specifically focalizing on wine label retrieval. In particular, Convolutional Neural Network (CNN) is utilized to filter out the impossible main-brands (manufacturers) for narrowing down the range of retrieval and the Speeded Up Robust Features (SURF) matching is improved by adopting the RANdom SAmple Consensus (RANSAC) mechanism and the modified Term Frequency-Inverse Document Frequency (TF-IDF) distance for the accurate retrieval of the sub-brand (item attribute under the manufacture). The experiments are conducted on a dataset containing approximately 548k images of wine labels with 17, 328 main-brands and 260, 579 subbrands. It is demonstrated by the experimental results that our proposed method can solve the wine label retrieval problem effectively and efficiently. Moreover, our proposed method is further evaluated on two pubic benchmarks of the object identification image retrieval tasks, Oxford Buildings Benchmark (Oxford5k) and the University of Kentucky of Indoor Things Benchmark (UKB), and achieves 88.3% mean average precision and 3.92 N-S score in Oxford5k and UKB, respectively. INDEX TERMS Image retrieval, object identification, wine label retrieval, CNN, SURF descriptor, filter out the impossible main-brands.

show abstract

Section: Cscfm Retrieval and Comparison On Oxford Buildings Datasetmentioning

confidence: 73%

Large Scale Category-Structured Image Retrieval for Object Identification Through Supervised Learning of CNN and SURF-Based Matching

Yang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In this section, two adjacent unfolded images, as shown in Figure 16a,c, were used to confirm the validity of the proposed PTSAD algorithm for an automatic image mosaic. In order to compare the feasibility and effectiveness of the proposed method with other established algorithms, we conducted the same experiments on the image matching by the feature-based of SIFT [36] and the full-search (FS) of NCC and SAD [37]. Figure 16a,c are the resource image and the examined image in the template matching respectively.…”

Section: Borehole Wall Unfolded Images Matching Experimentsmentioning

confidence: 99%

Generating a Cylindrical Panorama from a Forward-Looking Borehole Video for Borehole Condition Analysis

et al. 2019

View full text Add to dashboard Cite

Geological exploration plays a fundamental and crucial role in geological engineering. The most frequently used method is to obtain borehole videos using an axial view borehole camera system (AVBCS) in a pre-drilled borehole. This approach to surveying the internal structure of a borehole is based on the video playback and video screenshot analysis. One of the drawbacks of AVBCS is that it provides only a qualitative description of borehole information with a forward-looking borehole video, but quantitative analysis of the borehole data, such as the width and dip angle of fracture, are unavailable. In this paper, we proposed a new approach to create a whole borehole-wall cylindrical panorama from the borehole video acquired by AVBCS, which provides a possibility for further analysis of borehole information. Firstly, based on the Otsu and region labeling algorithms, a borehole center location algorithm is proposed to extract the borehole center of each video image automatically. Afterwards, based on coordinate mapping (CM), a virtual coordinate graph (VCG) is designed in the unwrapping process of the front view borehole-wall image sequence, generating the corresponding unfolded image sequence and reducing the computational cost. Subsequently, based on the sum of absolute difference (SAD), a projection transformation SAD (PTSAD), which considers the gray level similarity of candidate images, is proposed to achieve the matching of the unfolded image sequence. Finally, an image filtering module is introduced to filter the invalid frames and the remaining frames are stitched into a complete cylindrical panorama. Experiments on two real-world borehole videos demonstrate that the proposed method can generate panoramic borehole-wall unfolded images from videos with satisfying visual effect for follow up geological condition analysis. From the resulting image, borehole information, including the rock mechanical properties, distribution and width of fracture, fault distribution and seam thickness, can be further obtained and analyzed.

show abstract

“…Las redes neuronales convolucionales (CNNs) se han usado últimamente en tareas de análisis de imágenes, sobretodo destacando su uso en los procedimientos de clasificación y reconocimiento (Zhang et al, 2017). Este modelo de red se ha desarrollado inspirado en el sistema de aprendizaje biológico.…”

Section: Red Neuronal Convolucionalunclassified

Técnicas de inteligencia artificial utilizadas en el procesamiento de imágenes y su aplicación en el análisis de pavimentos

Reyes-Ortiz

Mejía

Useche-Castelblanco

2019

reveia

View full text Add to dashboard Cite

Debido al incremento en los costos de mantenimiento, rehabilitación y construcción de vías, estudiar las estructuras de pavimento para determinar su comportamiento y sus características mecánicas propias analizando la distribución y posición de sus partículas, se ha vuelto un campo de gran importancia en la ingeniería. Las nuevas herramientas de análisis buscan hacer este estudio más eficiente reduciendo su costo y tiempo de ejecución mediante el procesamiento digital de imágenes. El procesamiento digital tradicional está limitado en su sensibilidad ante perturbaciones externas que puedan modificar la imagen, por eso se han implementado diferentes técnicas de inteligencia artificial (IA) para optimizar los algoritmos. Este trabajo presenta una revisión de las diferentes aplicaciones de técnicas de IA recientes en el procesamiento de imágenes. Después se revisan los trabajos realizados específicamente con imágenes de pavimentos y se proponen posibles aplicaciones para implementar en este campo con inteligencia artificial

show abstract

SIFT Matching with CNN Evidences for Particular Object Retrieval

Cited by 30 publications

References 15 publications

Large Scale Category-Structured Image Retrieval for Object Identification Through Supervised Learning of CNN and SURF-Based Matching

Large Scale Category-Structured Image Retrieval for Object Identification Through Supervised Learning of CNN and SURF-Based Matching

Generating a Cylindrical Panorama from a Forward-Looking Borehole Video for Borehole Condition Analysis

Técnicas de inteligencia artificial utilizadas en el procesamiento de imágenes y su aplicación en el análisis de pavimentos

Contact Info

Product

Resources

About