I'm Aymane Lakouiss, a PhD candidate in artificial intelligence applied to image analysis and a Research Engineer specializing in deep learning and computer vision.
I’m Aymane Lakouiss, a PhD candidate in artificial intelligence applied to image analysis and a Research Engineer specializing in deep learning and computer vision. I trained at ENSEIRB-MMATMECA in signal processing, image processing, and AI, and hold a Master’s in Systems Engineering for Signal and Image Processing. My focus is on developing AI-powered image analysis methods for cosmetic applications and imaging science.
My work spans CNN-based segmentation and classification, data-driven analysis, and translating results into actionable insights for cosmetic treatment assessment. I enjoy solving complex problems, collaborating across disciplines, and applying rigorous mathematics and engineering to real-world vision challenges.
⋄ Development of artificial intelligence–based cosmetic image analysis
methods to automate the evaluation of facial youth-related characteristics.
⋄ Design and adaptation of deep learning models (segmentation and classification) based on CNN architectures to improve the accuracy and robustness
of the analyses.
⋄ Exploitation of analysis results to assess the effectiveness of cosmetic
treatments and to study correlations between youth indicators and treatment
types.
⋄ Improvement of a deep learning model for the automatic extraction of
walls, doors, and windows from architectural floor plan images.
⋄ Optimization of model architecture, hyperparameters, and data augmentation techniques to enhance accuracy.
⋄ Development of post-processing methods to refine vectorization, including
point realignment and segment merging.
Development of artificial intelligence–based cosmetic image analysis methods to automate the evaluation of facial youth-related characteristics. Design and adaptation of deep learning models (segmentation and classification) based on CNN architectures to improve the accuracy and robustness of the analyses. Exploitation of analysis results to assess the effectiveness of cosmetic treatments and to study correlations between youth indicators and treatment types.
Development of AI-based cosmetic image analysis methods to automate evaluation of facial youth-related characteristics. Design and adaptation of deep learning models (segmentation and classification) based on CNN architectures to improve accuracy and robustness. Exploitation of analysis results to assess effectiveness of cosmetic treatments and study correlations between youth indicators and treatment types.
Improvement of a deep learning model for automatic extraction of walls, doors, and windows from architectural floor plan images. Optimization of model architecture, hyperparameters, and data augmentation techniques to enhance accuracy. Development of post-processing methods to refine vectorization, including point realignment and segment merging.
Post a job and invite Aymane, or contact them directly. No hidden commission.
