Least square and Gaussian process for image based microalgal density estimation

Nguyen, Linh; Nguyen, D. T.; Nghiem, Truong X.; Nguyen, Thang

doi:10.1016/j.compag.2021.106678

Cited by 13 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the averaged grayscale tones and their corresponding algal densities are then correlated in training a linear regression model, which can be used to predict density of algae from their image. As discussed in [13], GS2 presents outperformance as compared with ITU or GS1.…”

Section: Introductionmentioning

confidence: 86%

“…Microalgal density parameter is defined as the the number of algal cells per ml [2,13]. And an accurate method to obtain this number is carefully examining an aliquot through a microscope [10].…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, some methods were proposed to indirectly estimate density of microalgae by measuring some biological and physicochemical parameters, as briefly summarized in a review paper [14]. Recently, given advancement in the image processing techniques and thanks to low-cost camera sensors, image based methods are more and more widely employed in estimating density of microalgae [2,7,10,13,[15][16][17][18]. Specifically, images of microalgae can be captured by a camera and then analysed by an image processing technique, where extracted information can be utilized to calculate density of microalgae presented in the images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Convolutional neural network regression for low-cost microalgal density estimation

Nguyen¹,

Nguyen²,

Nghiem³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Density of microalgae is critical information for production of algae in a closed cultivation system since it can be used to optimally control their growth rate, biomass concentration and quality of the products. Given advancement in image processing techniques and thanks to low-cost camera sensors, image based methods are increasingly widely utilized to indirectly estimate the density. Advantages of the image based techniques include being less invasive and more nondestructive and biosecured. However, most of the existing techniques rely on averaging all pixels of a microalgae image, which may eliminate crucial information of their spatial correlation. Therefore, in this work we propose to exploit a convolutional neural network (CNN) to efficiently extract information from the microalgae images, which are then employed to regress the density. Interestingly, the proposed deep CNN regression model accepts the whole color image as its input while the density is calculated in the output. The proposed CNN regression architecture was validated in real-world experiments where the microalgal strain Chlorella vulgaris was cultured and their images were captured by our low-cost camera sensor system. The obtained results demonstrate that the averaged estimation accuracy of the proposed model is 0.55\% (+/- 0.68\%) while the R2 value between the density predictions and the ground truths is 0.9997, which is highly accurate and practical.

show abstract

Section: Introductionmentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional neural network regression for low-cost microalgal density estimation

Nguyen¹,

Nguyen²,

Nghiem³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…After being taken by the camera at resolution of 600 × 800 pixels, the images are sent to the image processor, which is implemented on a Raspberry Pi 3 B + for preprocessing and training a learning model [18] , [19] . The model is then utilized to predict density of microalgae presenting in a specific microalgal image.…”

Section: Hardware Descriptionmentioning

confidence: 99%

“…The image is then sent to the Raspberry Pi 3 Model B + for preprocessing. Features are also extracted on each image, which are then input into a learning model [18] , [19] to predict density of the microalgae captured in the image. Processing the microalgae image and predicting the microalgal density are manipulated by the program Main.py .…”

Section: Operation Instructionsmentioning

confidence: 99%