Machine Learning in Detection and Classification of Leukemia Using Smear Blood Images: A Systematic Review

Table 2

The most common features used in blast analysis using ML.

Class of features	Parameters
Color features	(i) Mean color intensity for red component; (ii) Mean color intensity for green component; (iii) Mean color intensity for blue component; (iv) Mean color intensity for hue component; (v) Mean color intensity for saturation component; (vi) Mean color intensity for value component
Texture features	(i) Homogeneity; (ii) Contrast; (iii) Correlation; (iv) Energy
Statistical features	(i) Mean; (ii) Variance; (iii) Skewness
Wavelet features	(i) Mean of HARR A coefficient; (ii) Mean of HARR H coefficient; (iii) Mean of HARR V coefficient; (iv) Variance of HARR A coefficient; (v) Variance of HARR H coefficient; (vi) Variance of HARR V coefficient
Morphological features	(i) Area, perimeter, roundness, elongation, form factor, length-to-diameter ratio, compactness, discrete Fourier transform