Embedded registration of visible and infrared images in real time for noninvasive skin cancer screening

Inostroza, Fabian; Diaz, Silvana; Cardenas, Javier; Godoy, Sebastián

doi:10.1016/j.micpro.2017.09.006

Cited by 9 publications

(12 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This submodule calculates the average of the intensities of the pixels in the region of interest, using the image obtained after applying the mask. This implementation is based on the Equations ( 5), ( 7) and (9).…”

Section: Mean Calculation Submodulementioning

confidence: 99%

See 1 more Smart Citation

Proposal of the CAD System for Melanoma Detection Using Reconfigurable Computing

Barros

Morais

Lopes

et al. 2020

Sensors

View full text Add to dashboard Cite

This work proposes dedicated hardware to real-time cancer detection using Field-Programmable Gate Arrays (FPGA). The presented hardware combines a Multilayer Perceptron (MLP) Artificial Neural Networks (ANN) with Digital Image Processing (DIP) techniques. The DIP techniques are used to extract the features from the analyzed skin, and the MLP classifies the lesion into melanoma or non-melanoma. The classification results are validated with an open-access database. Finally, analysis regarding execution time, hardware resources usage, and power consumption are performed. The results obtained through this analysis are then compared to an equivalent software implementation embedded in an ARM A9 microprocessor.

show abstract

Section: Mean Calculation Submodulementioning

confidence: 99%

“…The work of [9] proposes an embedded system for recording real-time multimodal images applied to non-invasive tracking of skin cancer. The work presents the development of a hybrid architecture of hardware and software, implemented in a Xilinx Z-7010 SoC device.…”

Section: Introductionmentioning

confidence: 99%

Proposal of the CAD System for Melanoma Detection Using Reconfigurable Computing

Barros

Morais

Lopes

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…We use the projective transformation, which is the most general transformation that uses homogeneous coordinates and allows us to compensate for rotation, translation, scaling and perspective differences between the visible-range and IR cameras. To estimate a projective transformation [42], denote the mapping of a point u = [u x u y u w ] T onto a point v in homogenous coordinates as…”

Section: Image Registration Algorithmmentioning

confidence: 99%

“…. , θ 7 are computed using the coordinates of the four marker-corners in the visible-range and IR images using gradient descent [42].…”

Section: Image Registration Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

An Instrument for Accurate and Non-Invasive Screening of Skin Cancer Based on Multimodal Imaging

et al. 2019

Self Cite

View full text Add to dashboard Cite

We present an instrument based on commodity embedded hardware, that implements an automatic procedure for early skin-cancer screening using dynamic thermal imaging. The procedure leverages image segmentation in the visible range and real-time multimodal registration to compute the temperature recovery curve (TRC) of suspicious skin lesions using thermal infrared video. The instrument implements two algorithms that infer the malignancy of the lesion from the computed TRCs. The first algorithm assumes that the TRCs are deterministic and infers the malignancy from the distance between the TRC of the suspicious lesion and its surrounding skin, which is assumed to be healthy tissue. The second algorithm models the TRC of the lesion as a random process and uses detection theory to statistically infer its malignancy from the eigenfunctions and corresponding eigenvalues of its covariance function. We built a prototype of the instrument using a Raspberry Pi 3 model B+ board, which acquires a visible-range image of the lesion at the beginning of the procedure and performs image segmentation in 62ms. Operating on a 400 × 400-pixel region-of-interest within the infrared video, the board performs frame-by-frame multimodal image registration and generates the TRCs in real time at more than 37 frames per second, thus eliminating the need to store video data for off-line processing. The statistical detection algorithm, which yields the best results, runs in 1.07s at the end of the procedure, and achieves a sensitivity of 98% and a specificity of 95% on a dataset of 116 volunteer subjects.

show abstract

Vine disease detection in UAV multispectral images using optimized image registration and deep learning segmentation approach

Kerkech

Hafiane

Canals

2020

Computers and Electronics in Agriculture

201

View full text Add to dashboard Cite

Embedded registration of visible and infrared images in real time for noninvasive skin cancer screening

Cited by 9 publications

References 6 publications

Proposal of the CAD System for Melanoma Detection Using Reconfigurable Computing

Proposal of the CAD System for Melanoma Detection Using Reconfigurable Computing

An Instrument for Accurate and Non-Invasive Screening of Skin Cancer Based on Multimodal Imaging

Vine disease detection in UAV multispectral images using optimized image registration and deep learning segmentation approach

Contact Info

Product

Resources

About