Perfect pixel count

A simple model

Axis offers a simplified model of a complex reality.

As with the analog percentage method, operational requirements should be specified at a point or line at 90 degrees of the camera axis in the field of view. This is vital, since the further from the camera an object is, the lesser the pixel density. We call this imaginary line across the field of view the capture line. Rather than using people’s heads as a yardstick, we use a standardized measurement instead.

Table 4 illustrates the operational requirements for an average face, and the calculations for pixel density. Once we know these figures, we can use them in different ways. Figure 1 illustrates the three operational criteria, with recognition shown on the left and detection shown on the right.

Operational requirement Horizontal pixels / Face Pixels / cm Pixels / inch
Identification (Challenging conditions) 80 px/face 5 px/cm 12,5 px/in
Identification (Good conditions³) 40 px/face 2,5 px/cm 6,3 px/in
Recognition 20 px/face 1,25 px/cm 3,2 px/in
Detection 4 px/face 0,25 px/cm 0,6 px/in


Table 4. Operational requirements for an average human face.

Figure 1. Examples of how the three operational requirement criteria can appear.

Use the model